review-pr

Invocation: User- and model-invocable
Argument hint: [PR number or URL]
Allowed tools: Bash(${CLAUDE_PLUGIN_ROOT}/scripts/config-*), Bash(${CLAUDE_PLUGIN_ROOT}/skills/github/scripts/*)
Source: skills/github/review-pr/SKILL.md

Review PR

!${CLAUDE_PLUGIN_ROOT}/scripts/config-read-context.sh !${CLAUDE_PLUGIN_ROOT}/scripts/config-read-skill-context.sh review-pr !${CLAUDE_PLUGIN_ROOT}/scripts/config-read-agents.sh

If no “Agent Names” section appears above, use these defaults: accelerator:reviewer, accelerator:codebase-locator, accelerator:codebase-analyser, accelerator:codebase-pattern-finder, accelerator:documents-locator, accelerator:documents-analyser, accelerator:web-search-researcher.

!${CLAUDE_PLUGIN_ROOT}/scripts/config-read-review.sh pr

PR reviews directory: !${CLAUDE_PLUGIN_ROOT}/scripts/config-read-path.sh review_prs Tmp directory: !${CLAUDE_PLUGIN_ROOT}/scripts/config-read-path.sh tmp

IMPORTANT: Wherever {tmp directory} or {pr reviews directory} appears in the instructions below, substitute the actual resolved path shown above. Never use /tmp or any other path not shown above.

IMPORTANT: When composing prompts for sub-agents, resolve all {...} path placeholders to their actual values before passing the prompt — sub-agents cannot see the bold-label definitions above and have no way to resolve the placeholders themselves.

PR Review Template

The template below defines the frontmatter and body structure that every PR review must carry. Read it now — use it to guide what information you record in Steps 3-4 and what shape you persist in Step 4.10.

!${CLAUDE_PLUGIN_ROOT}/scripts/config-read-template.sh pr-review

You are tasked with reviewing a pull request through multiple quality lenses and then presenting a compiled analysis of the code changes.

Initial Response

When this command is invoked:

Check if a PR number or URL was provided:

If a PR number or URL was provided as an argument, identify the PR immediately
If optional focus arguments were provided (e.g., “focus on security and architecture”), note them for lens selection
Begin the review process

If no argument provided, respond with:

I'll help you review a pull request. Please provide:
1. The PR number or URL (or I'll check the current branch)
2. (Optional) Focus areas to emphasise (e.g., "focus on security and
   architecture")

Tip: You can invoke this command with arguments:
  `/review-pr 123`
  `/review-pr 123 focus on security and test coverage`

Then check if the current branch has a PR: gh pr view --json number,url,title,state 2>/dev/null

If a PR is found on the current branch, offer to review it. If not, wait for the user’s input.

Available Review Lenses

Lens	Lens Skill	Focus
Architecture	`architecture-lens`	Modularity, coupling, dependency direction, structural drift
Security	`security-lens`	OWASP Top 10, input validation, auth/authz, secrets, data flows
Test Coverage	`test-coverage-lens`	Coverage adequacy, assertion quality, test pyramid, anti-patterns
Code Quality	`code-quality-lens`	Complexity, design principles, error handling, code smells
Standards	`standards-lens`	Project conventions, API standards, naming, accessibility
Usability	`usability-lens`	Developer experience, API ergonomics, configuration, onboarding
Performance	`performance-lens`	Algorithmic efficiency, resource usage, concurrency, caching
Documentation	`documentation-lens`	Documentation completeness, accuracy, audience fit
Database	`database-lens`	Migration safety, schema design, query correctness, integrity
Correctness	`correctness-lens`	Logical validity, boundary conditions, state management, concurrency
Compatibility	`compatibility-lens`	API contracts, cross-platform, protocol compliance, deps
Portability	`portability-lens`	Environment independence, deployment flexibility, vendor lock
Safety	`safety-lens`	Data loss prevention, operational safety, protective mechanisms

Process Steps

Step 1: Identify and Fetch the PR

Get PR metadata: gh pr view {number} --json number,url,title,state,baseRefName,headRefName
Create temp directory at {tmp directory}/pr-review-{number} (substituting the actual PR number):
Terminal window
```
mkdir -p {tmp directory}/pr-review-{number}
```

Fetch diff, changed files, PR description, and commit context:

gh pr diff {number} > {tmp directory}/pr-review-{number}/diff.patch
gh pr diff {number} --name-only > {tmp directory}/pr-review-{number}/changed-files.txt
gh pr view {number} --json body --jq '.body' > {tmp directory}/pr-review-{number}/pr-description.md
gh pr view {number} --json commits --jq '.commits[].messageHeadline' > {tmp directory}/pr-review-{number}/commits.txt

Read the diff, changed files list, PR description, and commits to understand scope and intent.

Fetch additional metadata for the Reviews API:

gh api repos/{owner}/{repo}/pulls/{number} --jq '.head.sha' > {tmp directory}/pr-review-{number}/head-sha.txt
${CLAUDE_PLUGIN_ROOT}/skills/github/scripts/pr-base-repo.sh {number} > {tmp directory}/pr-review-{number}/repo-info.txt

Where {owner} and {repo} are extracted from the PR metadata already fetched in step 1.

Error handling: If any gh command fails, handle these cases:

gh not installed or not authenticated: Inform the user that the gh CLI is required and suggest running gh auth login to authenticate.
No default remote repository: Instruct the user to run gh repo set-default and select the appropriate repository (mirrors the pattern in /describe-pr).
Cannot determine base repo owner/name: If pr-base-repo.sh exits non-zero, surface its stderr verbatim — it preserves the underlying gh error and includes a gh repo set-default remediation hint when applicable.
Invalid PR number or PR not found: Inform the user that the PR could not be found and suggest checking the number. If on a branch with no PR, list open PRs with gh pr list --limit 10 and ask the user to select one.
Empty diff: If diff.patch is empty (e.g., a draft PR with no changes), inform the user and use the AskUserQuestion tool with two options:
1. Yes, review description and commits only — proceed without a diff
2. No, abort — exit without reviewing

Step 2: Select Review Lenses

Determine which lenses are relevant based on the PR’s scope and any user-provided focus arguments.

If the user provided focus arguments:

Map the focus areas to the corresponding lenses
Include any additional lenses that are clearly relevant to the PR’s scope
Briefly explain which lenses you’re running and why

If no focus arguments were provided, auto-detect relevance:

Take time to think carefully about which lenses apply based on:

Architecture — relevant for most PRs; skip only for trivial single-file changes
Security — relevant when changes involve: user input handling, auth/authz, data storage, external integrations, API endpoints, secrets/config
Test Coverage — relevant for most PRs; skip only for documentation-only or configuration-only changes
Code Quality — relevant for most PRs; skip only for documentation-only changes
Standards — relevant when changes involve: API changes, new files/modules, public interfaces, naming-heavy changes
Usability — relevant when changes involve: public APIs, CLI interfaces, configuration surfaces, breaking changes, developer-facing libraries
Performance — relevant when changes involve: data processing, API endpoints handling load, algorithm-heavy code, concurrency resource efficiency, caching logic, or hot code paths. Skip for documentation-only, configuration-only, or simple UI changes.
Documentation — relevant when changes involve: public APIs, README files, configuration surfaces, new features that need documentation, breaking changes requiring migration guides. Skip for internal refactoring with no interface changes.
Database — relevant when changes involve: database migrations, schema changes, new queries, ORM model changes, transaction logic, connection pool configuration. Skip for changes with no database interaction.
Correctness — relevant for most PRs; skip only for documentation-only, configuration-only, or simple renaming changes.
Compatibility — relevant when changes involve: public API modifications, dependency updates, serialisation format changes, cross-platform code, protocol implementations. Skip for internal-only changes with no external consumers.
Portability — relevant when changes involve: infrastructure configuration, deployment scripts, containerisation, cloud provider integrations, environment-specific code paths. Skip for application logic with no environment dependencies.
Safety — relevant when changes involve: data deletion or modification operations, deployment configuration, automated batch processes, infrastructure changes, feature flags, or critical system components. Skip for read-only features, documentation, or UI-only changes.

Lens selection cap: Select the most relevant lenses for the change under review. If review configuration is provided above, use the configured min_lenses and max_lenses values. Otherwise, use the defaults: {min lenses} to {max lenses} lenses. Apply these prioritisation rules:

Apply this lens selection pipeline in order:

Start with all available lenses: the 13 built-in lenses plus any custom lenses listed in the review configuration above.
Remove disabled lenses: if review configuration specifies disabled_lenses, remove those from the available set. They are never selected regardless of auto-detect criteria.
Mark core lenses: if review configuration specifies core_lenses, use that list. Otherwise, the core lenses are Architecture, Code Quality, Test Coverage, and Correctness. Core lenses are included unless the change is clearly outside their scope.
Auto-detect remaining lenses: use the criteria below (for built-in lenses) and the auto-detect criteria from review configuration (for custom lenses) to identify which non-core lenses are relevant to the change. Custom lenses that provide auto-detect criteria participate in selection like any other non-core lens. Custom lenses without auto-detect criteria (marked “always include” in the configuration) are always selected. Custom lenses use absolute paths instead of the ${CLAUDE_PLUGIN_ROOT} lens path template.
Apply focus arguments: if the user provided focus areas, prioritise the corresponding lenses and fill remaining slots with auto-detected ones.
Cap at max_lenses: if more lenses than the configured maximum pass selection, rank by relevance and drop the least relevant. Prefer lenses whose core responsibilities directly overlap with the change’s concerns.
Enforce min_lenses floor: never run fewer than min_lenses unless the change is trivially scoped.

When presenting the lens selection, clearly indicate which lenses are selected and which are skipped, with a brief reason for each skip.

Present lens selection to the user before proceeding:

Based on the PR's scope, I'll review through these lenses:
- Architecture: [reason]
- Security: [reason — or "Skipping: no security-sensitive changes identified"]
- Test Coverage: [reason]
- Code Quality: [reason]
- Standards: [reason — or "Skipping: ..."]
- Usability: [reason — or "Skipping: ..."]
- Performance: [reason — or "Skipping: no performance-sensitive changes identified"]
- Documentation: [reason — or "Skipping: ..."]
- Database: [reason — or "Skipping: no database changes identified"]
- Correctness: [reason]
- Compatibility: [reason — or "Skipping: ..."]
- Portability: [reason — or "Skipping: ..."]
- Safety: [reason — or "Skipping: ..."]

Then use the AskUserQuestion tool to ask the user whether to proceed, with two options:

Yes, use the proposed lenses — run the review with the selected lenses
No, specify which lenses to use — adjust the selection before running

Wait for the user’s answer before spawning reviewers. If they choose option 2, ask which lenses they want using a plain-text question only — do NOT use AskUserQuestion for this follow-up (the lens list is too large for the 4-option limit). If any lens name is unrecognised, seek clarification. Once confirmed, update the selection and re-present it using the same AskUserQuestion proceed/adjust pattern. This loop is user-controlled with no hard termination limit.

Step 3: Spawn Review Agents

For each selected lens, spawn the {reviewer agent} agent with a prompt that includes paths to the lens skill and output format files. Do NOT read these files yourself — the agent reads them in its own context.

Reminder: In the template below, replace {tmp directory} with the actual path resolved at the top of this skill before passing the prompt to the agent.

Compose each agent’s prompt following this template:

You are reviewing pull request changes through the [lens name] lens.

## Context

The PR artefacts are in the temp directory at {tmp directory}/pr-review-{number}:
- `diff.patch` — the full diff
- `changed-files.txt` — list of changed file paths
- `pr-description.md` — PR description
- `commits.txt` — commit messages

PR number: [number]

## Analysis Strategy

1. Read your lens skill and output format files (see paths below)
2. Read `diff.patch` and `changed-files.txt` from the temp directory
3. Read `pr-description.md` and `commits.txt` for intent context
4. Explore the codebase to understand the architectural landscape around
   the changes
5. Evaluate the changes through your lens, applying each key question
6. Identify beyond-the-diff impact — trace how changes affect consumers
7. Anchor findings to precise diff line numbers (lines must be within
   diff hunks)

## Lens

Read the lens skill at the path listed in the Lens Catalogue table in the
review configuration above. If no review configuration is present, use:
${CLAUDE_PLUGIN_ROOT}/skills/review/lenses/[lens]-lens/SKILL.md

## Output Format

Read the output format at: ${CLAUDE_PLUGIN_ROOT}/skills/review/output-formats/pr-review-output-format/SKILL.md

IMPORTANT: Return your analysis as a single JSON code block. Do not include
prose outside the JSON block.

Spawn all selected agents in parallel using the Task tool with subagent_type: "!${CLAUDE_PLUGIN_ROOT}/scripts/config-read-agent-name.sh reviewer".

IMPORTANT: Wait for ALL review agents to complete before proceeding.

Handling malformed agent output:

If an agent’s response is not a clean JSON block, apply this extraction strategy:

Look for a JSON code block fenced with triple backticks (optionally with a json language tag)
If found, extract and parse the content within the fences
If the extracted JSON is valid, use it normally
If no JSON code block is found, or the JSON within it is invalid, apply the fallback: treat the agent’s entire output as a single general finding with the agent’s lens name and "major" severity, and include it in the review summary body

When falling back, warn the user that the agent’s output could not be parsed and present the raw agent output in a collapsed form so the user can see what the agent actually found.

Step 4: Aggregate and Curate Findings

Once all reviews are complete:

Parse agent outputs: Extract the JSON block from each agent’s response (see the extraction strategy in Step 3). Collect the summary, strengths, comments, and general_findings arrays from each.
Aggregate across agents:
- Combine all comments arrays into a single list
- Combine all general_findings arrays into a single list
- Combine all strengths arrays into a single list
- Collect all summary strings
Validate line numbers against the diff: Parse the hunk headers in diff.patch to build valid line ranges per file. For each @@ header:
- Extract the new-file range from @@ -a,b +c,d @@ — lines c through c+d-1 are valid RIGHT-side lines
- Extract the old-file range — lines a through a+b-1 are valid LEFT-side lines
- For each comment in the aggregated comments list, check that its path/line/side falls within a valid range for that file
- Move any comments with out-of-range lines to general_findings automatically, preserving all their metadata (severity, lens, title, body)
- If a comment was moved, note it in the preview so the user knows
Deduplicate inline comments: Where multiple agents flag the same file, same side, and overlapping or adjacent line range (same path, lines within the configured dedup proximity ({dedup proximity}) of each other), consider merging — but only when the findings address the same underlying concern from different lens perspectives. Spatial proximity alone is not sufficient; the findings must be semantically related.

When merging:
- Combine the bodies, attributing each part to its lens
- Use the highest severity among the merged findings
- Use the highest confidence among the merged findings
- Note all contributing lenses in the title
When in doubt, keep comments separate — distinct inline comments are easier to resolve individually on GitHub than a merged comment covering multiple concerns.
Prioritise and cap inline comments:
- Sort by severity: critical > major > minor > suggestion
- Within the same severity, sort by confidence: high > medium > low
- Always include all critical findings, even if that exceeds {max inline comments}
- Select up to the configured max inline comments ({max inline comments}) comments total for inline posting (more if all critical findings push beyond the cap)
- Move any remaining comments to the summary body as an “Additional Findings” list (title + file:line only)
Determine suggested verdict:

If review configuration provides verdict overrides above, apply those thresholds instead of the defaults below:
- If pr_request_changes_severity is none, skip this rule (never suggest REQUEST_CHANGES based on severity)
- If any findings at or above the configured pr_request_changes_severity (default: critical) exist → suggest REQUEST_CHANGES
- If only findings below that threshold → suggest COMMENT
- If no findings at all (only strengths) → suggest APPROVE
Identify cross-cutting themes: Look for findings that appear across multiple lenses — issues flagged by 2+ agents reinforce each other and should be highlighted in the summary. Also identify tradeoffs where different lenses conflict (e.g., security wants more validation, usability wants less friction).

Compose the review summary body (this becomes the body field of the GitHub review):

## Code Review: #{number} - {title}

**Verdict:** [APPROVE | REQUEST_CHANGES | COMMENT]

[Combined assessment: take each agent's summary and synthesise into 2-3
sentences covering the overall quality of the PR across all lenses]

### Cross-Cutting Themes
[Issues that multiple lenses identified — these deserve the most attention]
- **[Theme]** (flagged by: [lenses]) — [description]

### Tradeoff Analysis
[Where different lenses disagree, present both perspectives]
- **[Quality A] vs [Quality B]**: [description and recommendation]

[Omit either section if there are no cross-cutting themes or tradeoffs]

### Strengths
- ✅ [Aggregated and deduplicated strengths from all agents]

### General Findings
- [emoji] **[Lens]**: [General findings from all agents, sorted by severity]

### Additional Findings
[Only if more than {max inline comments} inline comments were produced and
some were deferred]
- [emoji] `file:line` — [title] ([lens])

---
*Review generated by /review-pr*

Compose each inline comment body: Each comment’s body field should already be self-contained from the agent output. For merged comments, combine the bodies with a blank line separator and attribute each section to its lens.

Write the review artifact to {pr reviews directory}/:

Determine the next review number:

mkdir -p {pr reviews directory}
# Glob for existing reviews of this PR
ls {pr reviews directory}/{number}-review-*.md 2>/dev/null
# Extract the highest number, increment by 1. If none exist, use 1.

Write the review document to {pr reviews directory}/{number}-review-{N}.md.

Populate frontmatter

The target: field is filled automatically from the PR number — this is what makes the review traceable back to the PR it covers. Per ADR-0034, the typed-linkage form is "pr:<pr-number>".

Before writing the PR review file, capture metadata and substitute the unified base fields and per-type extras into the template’s frontmatter block:

Invoke ${CLAUDE_PLUGIN_ROOT}/scripts/artifact-derive-metadata.sh to obtain Current Date/Time (UTC):. Run the bare path directly as an executable; never prefix it with bash/sh/env (a wrapper prefix escapes the skill’s allowed-tools permission and forces an unnecessary prompt).
Substitute every field below with the indicated value:
- type: ← pr-review
- id: ← {number}-review-{N} (the review filename stem, where {number} is the PR number and {N} is the next review number), always quoted as a YAML string
- title: ← the PR title from gh pr view --json title
- date: ← the Current Date/Time (UTC): value
- author: ← the author value resolved per create-work-item/SKILL.md:578-580
- producer: ← review-pr
- status: ← complete
- last_updated: ← the same Current Date/Time (UTC): value
- last_updated_by: ← the same value resolved for author
- schema_version: ← 1 (bare integer, not quoted)
- parent: ← typed-linkage ref to the parent PR ("pr:NNNN"). Fill when the review names a parent; otherwise omit the key.
- target: ← "pr:<pr-number>" (e.g. "pr:123"); the typed-linkage ref to the PR under review per ADR-0034, must match the regex ^"pr:[0-9]+"$. Always fill — every review has a target.
- relates_to: ← list of typed-linkage refs to related reviews or artifacts (["pr-review:NNNN", ...]). Fill when prior reviews are explicit; otherwise omit the key.
- reviewer: ← the reviewer value resolved per create-work-item/SKILL.md:578-580
- verdict: ← the verdict from Step 4.6 (APPROVE | REQUEST_CHANGES | COMMENT)
- lenses: ← the list of lens names used
- review_number: ← N (the next available review number from the glob above)
- pr_number: ← the PR number from gh pr view --json number (bare integer; foreign reference to the external PR per ADR-0033 §Identity-value shape contract)
The PR title is recorded in the base title: field; no separate pr_title: field is emitted (the unified schema uses the base title: for all artifact titles per ADR-0033). The review_pass: field is intentionally absent — review-pr has no in-place re-review update flow today; re-running it produces a fresh -review-{N+1}.md.
Write the file with the substituted frontmatter block, followed by the review summary composed in Step 4.8 and the inline comments and per-lens results sections:

{The full review summary from Step 4.8}

## Inline Comments

### `{path}:{line}` — {title}
**Severity**: {severity} | **Confidence**: {confidence} | **Lens**: {lens}

{comment body}

---

### `{path}:{line}` — {title}
...

## Per-Lens Results

### {Lens 1 Name}

**Summary**: {agent summary}

**Strengths**:
{agent strengths}

**Comments**:
{agent comments — each with path, line, severity, confidence, and body}

**General Findings**:
{agent general findings}

### {Lens 2 Name}

...

This review artifact captures the complete analysis. The GitHub review (posted in Step 6) may be a curated subset (capped at ~{max inline comments} inline comments), but the persistent artifact retains everything.

Step 5: Present the Review

Present a two-part preview showing exactly what will be posted to the PR:

Part 1: Review summary (will become the review’s body):

Show the composed summary from Step 4.8 in a markdown code block so the user can see exactly what will be posted.

Part 2: Inline comments (will be attached to specific diff lines):

## Proposed Inline Comments ([count] comments)

### [file path 1]
- Line [N]: [emoji] **[Lens]** — [title]
  > [First 1-2 sentences of body as preview]

- Lines [N-M]: [emoji] **[Lens]** — [title]
  > [First 1-2 sentences of body as preview]

### [file path 2]
- Line [N]: [emoji] **[Lens]** — [title]
  > [First 1-2 sentences of body as preview]

[If comments were deferred due to the ~{max inline comments} cap:]
### Deferred to summary ([count] findings)
- [emoji] [Lens]: [title] — `file:line`

Step 6: Offer Actions

After presenting the preview:

The review is ready. Would you like to:
1. Post the review? (summary + [count] inline comments, verdict: [suggested verdict])
2. Change the verdict? (currently: [suggested verdict])
3. Edit or remove specific inline comments before posting?
4. Discuss any findings in more detail?
5. Re-run specific lenses with adjusted focus?

When the user chooses to post (option 1):

Read the HEAD SHA and repo info from the temp directory at {tmp directory}/pr-review-{number}/head-sha.txt and {tmp directory}/pr-review-{number}/repo-info.txt using the Read tool.
Construct the review payload as a JSON object containing:
- commit_id: the HEAD SHA
- body: the review summary composed in Step 4.8
- event: the verdict ("COMMENT", "REQUEST_CHANGES", or "APPROVE")
- comments: array of inline comment objects, each with:
  - path: file path from the agent’s comment
  - line: line number from the agent’s comment
  - side: side from the agent’s comment
  - body: the self-contained comment body
  - start_line and start_side: included only if end_line is not null. For multi-line comments, the agent’s fields map to the API’s fields with an inversion (see “Multi-Line Comment API Mapping” in Phase 1):
    - API start_line ← agent’s line (the beginning of the range)
    - API start_side ← agent’s side
    - API line ← agent’s end_line (the end of the range)
    - API side ← agent’s side
    Example: agent {line: 10, end_line: 15, side: "RIGHT"} becomes API {start_line: 10, start_side: "RIGHT", line: 15, side: "RIGHT"}
Write the review payload JSON to {tmp directory}/pr-review-{number}/review-payload.json, then post the review:
Terminal window
```
gh api repos/{owner}/{repo}/pulls/{number}/reviews \
  --method POST --input {tmp directory}/pr-review-{number}/review-payload.json
```
Where {owner}/{repo} are the values read from repo-info.txt.
Confirm success and show the PR URL:
Terminal window
```
gh pr view {number} --json url --jq '.url'
```

If the API returns a 422 error (typically an invalid line reference or stale commit):

Report the error to the user
If the error indicates an invalid line reference, identify which comment(s) caused the failure and offer to retry without them (move them to the summary)
If the error indicates a stale commit_id (the PR’s HEAD has changed since the review started), re-fetch the HEAD SHA and warn the user that new commits were pushed. Offer to retry with the updated SHA, noting that line numbers may have shifted and some comments may now be invalid

When the user chooses to edit comments (option 3):

Present each comment with a number
Allow the user to remove specific comments by number
Allow the user to edit a comment’s body text
After edits, re-present the preview and offer the same action options

When the user changes the verdict (option 2):

Use the AskUserQuestion tool with three options:
1. APPROVE — approve the PR
2. COMMENT — leave a non-blocking comment review
3. REQUEST_CHANGES — request changes before merge
Update the summary body and re-present the preview

Important Guidelines

Read the diff before doing anything else — you need complete context to select lenses and brief the agents properly
Spawn agents in parallel — the review lenses are independent and should run concurrently for efficiency
Synthesise, don’t concatenate — your value is in compiling a balanced view across lenses, identifying themes and tradeoffs, and prioritising actionable recommendations. Don’t just paste seven reports together.
Be balanced — highlight strengths alongside concerns. A PR that makes good architectural decisions but has security gaps should get credit for both.
Prioritise by impact — structural issues that are hard to fix later matter more than surface-level concerns. A critical finding from one lens outweighs minor findings from all seven.
Respect tradeoffs — when lenses conflict, present both sides and let the user decide. Don’t privilege one quality attribute over another without justification.
Clean up temp directory only at session end — agents may need to re-reference the PR context during follow-up discussion.

The {tmp directory}/pr-review-{number}/ directory contains ephemeral working data (diff, changed-files, PR description, commits, head SHA, repo info, review payload JSON) used during the review session. The review itself (summary, inline comments, per-lens results) is persisted separately to {pr reviews directory}/{number}-review-{N}.md.
Handle API errors gracefully — if the review post fails due to invalid line references, identify the problematic comments and offer to retry without them rather than failing entirely
Cap inline comments — if agents produce more findings, prioritise critical and major severity. Use the configured max ({max inline comments}). Always include all critical findings even if that exceeds the cap. Move overflow to the summary body. This prevents PR comment spam.
Keep positive feedback in the summary — strengths and good observations go in the review body, never as inline comments. Inline comments are exclusively for actionable findings.
Use emoji severity prefixes consistently — 🔴 critical, 🟡 major, 🔵 minor/suggestion, ✅ strengths. IMPORTANT: Use the actual Unicode emoji characters (🔴 🟡 🔵 ✅), NOT text shortcodes like :red_circle:, :yellow_circle:, :blue_circle:, or :white_check_mark:. Shortcodes are not rendered in markdown and will appear as literal text.

What NOT to Do

Don’t skip writing the review artifact — always persist to {pr reviews directory}/ so the full analysis is available to the team
Don’t post inline comments for positive feedback — strengths go in the summary only
Don’t post more than the configured max inline comments ({max inline comments}) inline comments — prioritise by severity (always include all critical findings even if that exceeds the cap)
Don’t post generic or vague inline comments — each must be specific and actionable
Don’t skip the preview step — always show the user what will be posted before posting
Don’t skip the lens selection step — always confirm with the user which lenses will run
Don’t present raw agent output — always aggregate and curate into the structured format
Don’t run lenses that clearly aren’t relevant
Don’t modify any code — this is a read-only review

Relationship to Other Commands

The PR review sits in the development lifecycle alongside other commands:

/create-plan — Create the implementation plan
/review-plan — Review and iterate the plan quality
/implement-plan — Execute the approved plan
/validate-plan — Verify implementation matches the plan
/describe-pr — Generate PR description
/review-pr — Review the PR through quality lenses (this command)

!${CLAUDE_PLUGIN_ROOT}/scripts/config-read-skill-instructions.sh review-pr