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 FeiZhuLulu/kimi-code-skills --skill self-reviewgit clone --depth 1 https://github.com/FeiZhuLulu/kimi-code-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/feizhululu/kimi-code-skills/self-review)<a href="https://agentmods.dev/skills/feizhululu/kimi-code-skills/self-review"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-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/feizhululu/kimi-code-skills/self-review"><img src="https://agentmods.dev/badge/skills/feizhululu/kimi-code-skills/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 | $0.00026 | $0.01709 |
| Opus 5 | $0.00013 | $0.00855 |
| Sonnet 5 | $0.00005 | $0.00342 |
| Haiku 4.5 | $0.00003 | $0.00171 |
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 10d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self Review — Pre-commit Change Review
Purpose
Review your local git changes before committing. This skill focuses on catching unintended edits, missing tests, debug leftovers, and risky changes — especially those introduced by AI agents during a coding session.
This is not a full PR review or security audit. It is a quick, structured sanity check before you commit.
Kimi Code Usage
Manual invocation:
/skill:self-review
/skill:self-review staged only
/skill:self-review security focus
Requested focus: $focus
Supported focus modes:
staged only— only review staged changessecurity focus— emphasize secret detection and security issues- (empty) — default: full checklist review
This skill may be automatically invoked when the user asks to review their changes before committing.
Workflow
1. Gather Changes
git status --short
git diff --stat
git diff --cached --stat
If there are both staged and unstaged changes, review staged changes for Commit Readiness. Report unstaged changes separately under Working Tree Notes.
If nothing is staged, report: Not ready — nothing staged unless the user explicitly asked to review unstaged work.
1.1 Determine Task Intent
Infer the intended task from the current Kimi conversation and recent user instructions.
- If the task goal is known, classify files against that goal.
- If the task goal is unknown, use
unclearinstead of pretending a file is intended or unrelated. - Only label a file
unrelatedwhen there is clear evidence: logs, generated artifacts, unrelated config, lockfiles, secret files, or files outside the stated task area.
2. Classify Each Changed File
Read the full diff:
git diff --cached # staged changes
git diff # unstaged changes
For each changed file, classify it:
| Category | Meaning |
|---|---|
| intended | Clearly matches the stated user task |
| suspicious | Risky, surprising, or possibly accidental |
| unrelated | Clearly outside the stated task |
| unclear | Cannot determine intent from available context |
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.
- 10d ago First seen · 210 lines · 26 tokens per session scan A 3e220d54ce57
self-review is a skill published in the GitHub repository FeiZhuLulu/kimi-code-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,709 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.