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 serejaris/kimi-skills --skill incident-review-guidegit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/incident-review-guide)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/incident-review-guide"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/incident-review-guide/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/serejaris/kimi-skills/incident-review-guide"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/incident-review-guide.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 | $0.00083 | $0.03031 |
| Opus 5 | $0.00042 | $0.01515 |
| Sonnet 5 | $0.00017 | $0.00606 |
| Haiku 4.5 | $0.00008 | $0.00303 |
Grade A, and why
incident-review-guide 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
incident-review-guide
A Blameless Postmortem writing workflow based on Google SRE and industry best practices. This structured SOP walks you through the full incident review process — from gathering incident details, building a timeline, conducting 5 Whys root cause analysis, to defining remediation actions — and produces a professional postmortem document.
Core philosophy: Blameless Culture — focus on improving systems and processes, not assigning blame to individuals.
Quick Start
Interactive review (recommended): Describe your incident and the Agent will guide you step by step through the SOP.
One-click document generation: If you already have complete incident details, use the script to quickly generate a formatted postmortem:
python3 scripts/generate_postmortem.py --interactive
Or provide JSON input to generate directly:
python3 scripts/generate_postmortem.py --input incident.json --output postmortem.md
SOP: Six Steps to a Professional Postmortem
Step 1: Incident Overview
Gather the following basic information to build the full picture:
| Field | Description | Example |
|---|---|---|
| Incident Title | Brief description of the failure | Payment service P99 latency spiked to 30s |
| Severity Level | P0–P3 (see grading criteria below) | P1 |
| Impact Start Time | When users were first affected | 2024-03-15 14:32 UTC+8 |
| Impact End Time | When the incident was fully resolved | 2024-03-15 16:45 UTC+8 |
| Duration | Auto-calculated or manually entered | 2h13m |
| Blast Radius | Affected users / services / regions | ~30% of users in East China region unable to complete payments |
| On-call / Response Team | Key personnel involved | SRE on-call: Alice, Payments team: Bob |
Severity Grading Criteria:
| Level | Definition | Typical Scenarios |
|---|---|---|
| P0 | Full site or core business unavailable, widespread user impact | Main site down, database cluster failure, payment system completely offline |
| P1 | Severe degradation of core features, significant portion of users affected | Search unavailable, order success rate dropped 50%, API error rate > 10% |
| P2 | Non-core features impaired, or minor degradation of core features | Recommendation engine latency increase, regional service anomaly, admin panel unavailable |
| P3 | Minor issue, users largely unaffected | Log collection delay, internal monitoring dashboard anomaly, non-critical cron job failure |
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.
- 9d ago First seen · 282 lines · 83 tokens per session scan A 016822e5b893
incident-review-guide is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 3,031 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…