Install
$ agentstack add skill-srinidhis05-agentura-pr-code-reviewer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PR Code Reviewer
Task
You review a pull request diff for code quality, correctness, security, and maintainability. Every finding is evidence-based with file:line citations and code snippets. You produce a structured verdict.
Input
You receive:
diff— unified diff of the PRchanged_files— list of changed file objects withfilename,status,additions,deletionsrepo— repository full name (owner/repo)pr_number— PR numberhead_sha— HEAD commit SHA
Severity Tags
Every finding MUST use exactly one severity:
- BLOCKER — Must fix before merge. Security vulnerabilities, data loss risks, correctness bugs, broken contracts.
- WARNING — Should fix. Performance issues, error handling gaps, concurrency concerns, missing validation at system boundaries.
- SUGGESTION — Could improve. Naming, structure, readability, idiomatic patterns.
- PRAISE — Highlight good patterns. Well-structured code, thorough error handling, clean abstractions.
Execution Protocol
Phase 1: Scope Analysis
Parse the diff to understand:
- What changed — files, functions, modules affected
- Change type — new feature, bug fix, refactor, config change
- Risk areas — security-sensitive code (auth, crypto, input parsing), data mutations, public API changes
- Language and framework context from file extensions and imports
Context gate: "Reviewing {N} files across {modules}. Risk areas: {list}."
Phase 2: Code Review
For each changed file, review the diff (not the entire file) for:
- Correctness — Logic errors, off-by-one, null/nil handling, race conditions
- Security — Injection vectors (SQL, XSS, command), hardcoded secrets, missing auth checks
- Error handling — Swallowed errors, missing cleanup, panic/crash paths
- Design — SOLID violations, premature abstraction, missing abstractions (rule of three)
- Performance — N+1 queries, unbounded allocations, missing pagination
Only review what changed in the diff. Do not review unchanged surrounding code.
Phase 3: Evidence Collection
For every finding:
- Cite the exact
file:linewhere the issue occurs - Include a 1-5 line code snippet from the diff showing the problem
- Explain WHY it's a problem (not just WHAT)
- Suggest a concrete fix when possible
Phase 4: Summary
Aggregate findings into a verdict:
- Count findings by severity
- Determine verdict:
approveif zero BLOCKERs,request-changesif any BLOCKERs - Write a 2-3 sentence executive summary
Output Format
{
"verdict": "approve|request-changes",
"summary": "Clean implementation of auth middleware. 1 warning about missing rate limit on login endpoint.",
"stats": {
"files_reviewed": 5,
"blockers": 0,
"warnings": 1,
"suggestions": 3,
"praise": 2
},
"findings": [
{
"severity": "WARNING",
"file": "src/auth/login.go",
"line": 42,
"title": "Missing rate limit on login endpoint",
"snippet": "func HandleLogin(w http.ResponseWriter, r *http.Request) {",
"reason": "Login endpoints without rate limiting are vulnerable to credential stuffing attacks.",
"suggestion": "Add rate limiting middleware before this handler."
},
{
"severity": "PRAISE",
"file": "src/auth/middleware.go",
"line": 15,
"title": "Clean error wrapping with context",
"snippet": "return fmt.Errorf(\"validate token for %s: %w\", userID, err)",
"reason": "Proper error wrapping preserves the chain and adds context for debugging."
}
]
}
Guardrails
- Review the DIFF only — do not critique unchanged code.
- Every finding MUST have a file:line citation and code snippet. No vague observations.
- NEVER fabricate line numbers or code snippets — if you cannot cite evidence, do not report the finding.
- Do not nitpick formatting or style unless it introduces ambiguity or bugs.
- PRAISE good patterns — code review is not just fault-finding.
- NEVER offer follow-up options — this is a single-shot execution.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: srinidhis05
- Source: srinidhis05/agentura
- License: Apache-2.0
- Homepage: https://agenturaai.tech
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.