Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Adit-Jain-srm/skill-forge --skill self-reviewgit clone --depth 1 https://github.com/Adit-Jain-srm/skill-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adit-jain-srm/skill-forge/self-review)<a href="https://agentmods.dev/skills/adit-jain-srm/skill-forge/self-review"><img src="https://agentmods.dev/badge/skills/adit-jain-srm/skill-forge/self-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adit-jain-srm/skill-forge/self-review"><img src="https://agentmods.dev/badge/skills/adit-jain-srm/skill-forge/self-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00824 |
| Opus 5 | $0.00034 | $0.00412 |
| Sonnet 5 | $0.00014 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
self-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Catch your own bugs, style issues, and missed requirements BEFORE presenting code. The user should never see your first draft.
Process
After writing or modifying code, review it yourself BEFORE presenting to the user.
Persistence
ACTIVE EVERY CODE CHANGE. Not a one-time thing. Every edit, every file, every commit-worthy change gets self-reviewed. Off only when user says "skip review" or "just do it".
The Review (run mentally, fix inline)
For each file you just modified:
1. RE-READ what you wrote (don't trust your memory of what you intended)
2. CHECK: Does this actually solve what was asked? (not a related thing, THE thing)
3. BUGS: Off-by-one? Null/undefined? Race condition? Unclosed resource?
4. EDGE CASES: Empty input? Very large input? Unicode? Concurrent access?
5. CONSISTENCY: Matches existing code style? Same naming conventions? Same patterns?
6. IMPORTS: Everything imported? Nothing unused? Circular dependency?
7. TYPES: Type-safe? No `any` where there shouldn't be? Generics correct?
8. ERROR HANDLING: What can throw? Is it caught? Is the error message useful?
9. TESTS: If tests exist, did I break any? Should I add one for this change?
10. SECURITY: User input validated? SQL injection? XSS? Auth checks?
Fix Before Showing
If you find an issue during self-review: fix it silently. Don't tell the user "I found a bug in my code." Just fix it. Present clean work.
The user should never see your first draft. They should see your REVIEWED draft.
What NOT to do
- Don't announce "I'm now reviewing my code" (just do it, silently)
- Don't present code then say "wait, let me fix something" (review BEFORE presenting)
- Don't skip review because "it's a small change" (small changes have bugs too)
- Don't review only the lines you changed (check surrounding context)
Depth Levels
| Change Size | Review Depth |
|---|---|
| 1-5 lines | Quick scan: bugs, types, imports |
| 5-50 lines | Full checklist above |
| 50+ lines | Full checklist + architecture fit + test impact |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 93 lines · 68 tokens per session scan A 2ca3b7a3d714
self-review is a skill published in the GitHub repository Adit-Jain-srm/skill-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 824 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
doc-drift
Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory…
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…