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 SteveVitali/agent-skills --skill self-reviewgit clone --depth 1 https://github.com/SteveVitali/agent-skillsWrote 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/stevevitali/agent-skills/self-review)<a href="https://agentmods.dev/skills/stevevitali/agent-skills/self-review"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/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/stevevitali/agent-skills/self-review"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/self-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00029 | $0.03091 |
| Opus 5 | $0.00015 | $0.01545 |
| Sonnet 5 | $0.00006 | $0.00618 |
| Haiku 4.5 | $0.00003 | $0.00309 |
Grade A, and why
self-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Review
A rigorous, two-pass review of all changes on the current branch. Pass 1 catches mechanical errors via automated checks and mechanical checklists. Pass 2 applies the deep design judgment of a senior Staff Engineer to catch the subtler issues that separate correct code from good code.
This workflow is designed to be invoked standalone on any branch, or as an
embedded step within a parent workflow (e.g., implement-spec).
Pass 1: Mechanical Verification
Purpose: eliminate the rote mistakes that waste human reviewer time. Every check here is binary — pass or fail, no judgment required.
Step 1.1 — Run automated verification
Run the repo's build/test/lint verification for the changeset. Resolve what to run in this order — use the first that applies:
-
Explicit command — the
verify_cmdinput or a$VERIFY_CMDenvironment variable. -
Repo-provided verification entry point — a canonical script or target the repo already defines: e.g.
./scripts/verify.sh,./bin/verify,make verify,make check, or the verification commands documented in the repo'sAGENTS.md/CONTRIBUTING.md. Prefer a changed-files-aware runner if the repo has one. -
The bundled inference helper —
scripts/verify.sh(shipped with this skill) detects the repo's toolchain(s) and runs their standard build/test/lint commands:scripts/verify.sh # exit 0 = pass, 1 = failures, 2 = could not infer -
Manual derivation — if the helper exits 2 (nothing inferable, or a build system like Bazel that needs targeted invocation), derive the exact commands from the repo's docs and build files for the packages you changed, and run those. Never skip verification silently — if truly nothing can be run, state that explicitly in the final summary.
If any check fails, diagnose and fix the issue before proceeding. Re-run until all checks pass. Maximum 3 fix iterations — if still failing after 3 attempts, report the remaining failures and stop.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 291 lines · 29 tokens per session scan A be0cc797217f
self-review is a skill published in the GitHub repository SteveVitali/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 3,091 once invoked, about $0.0001 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".