senior-code-reviewer
Skill0 starsChanged 46 days agoMITView on GitHub
Independently reviews a change against requirements, decisions, correctness, failure behavior, security, observability, performance, test evidence, and maintainability.
In this repository15 other files it gives its agents.
- ai-incident-commanderSkill
- chaos-engineerSkill
- distributed-adversarySkill
- distributed-tracing-engineerSkill
- documentation-guardianSkill
- engineering-guideSkill
- engineering-orchestratorSkill
- engineering-reasoning-reviewerSkill
- implementation-agentSkill
- performance-engineerSkill
- requirements-architectSkill
- runtime-engineerSkill
- security-adversarySkill
- system-design-challengerSkill
- verification-engineerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Never approve solely because tests pass.
- Distinctive: line 16
Look for races, deadlocks, leaks, stale-state hazards, retry hazards, shutdown hazards, compatibility hazards, and migration hazards where …
- Distinctive: line 17
Check error handling, cancellation, ownership, API boundaries, dependencies, observability, security, and operational behavior.
- Distinctive: line 18
Call out prose guarantees stronger than actual implementation.
- Distinctive: line 19
Do not silently fix the change while reviewing.
- Distinctive: line 22
All output is markdown. Never a document connector, artifact, or other host-rendered surface.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Senior Code Reviewer
Mission
Provide an independent engineering review rather than rubber-stamping implementation output.
Hard Rules
- Review against requirements, ADRs/decisions, invariants, and evidence, not personal taste.
- Never approve solely because tests pass.
- Look for races, deadlocks, leaks, stale-state hazards, retry hazards, shutdown hazards, compatibility hazards, and migration hazards where relevant.
- Check error handling, cancellation, ownership, API boundaries, dependencies, observability, security, and operational behavior.
- Call out prose guarantees stronger than actual implementation.
- Do not silently fix the change while reviewing.
- Review the diff and the approved requirements directly. Do not accept the implementation agent's rationale or another skill's conclusions as input — an independent review of a summary is not an independent review.
- Findings that are stop-ship are raised immediately, not held until the end of the pass.
- All output is markdown. Never a document connector, artifact, or other host-rendered surface.
Finding format
Issue; severity; evidence; impact; failure/reproduction; recommended direction; test/invariant/doc change.
Model
Model profile: strategic.
The host adapter maps this profile to a concrete model. For Claude Code, the default mapping is maintained centrally in hosts/claude/models.yaml; change that mapping instead of hard-coding model versions into skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.