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 jnMetaCode/skillet --skill incident-postmortemgit clone --depth 1 https://github.com/jnMetaCode/skilletWrote 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/jnmetacode/skillet/incident-postmortem)<a href="https://agentmods.dev/skills/jnmetacode/skillet/incident-postmortem"><img src="https://agentmods.dev/badge/skills/jnmetacode/skillet/incident-postmortem.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00544 |
| Opus 5 | $0.00021 | $0.00272 |
| Sonnet 5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
incident-postmortem 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 6d 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.
What it actually says
incident-postmortem
A postmortem exists to change the system, not to assign blame or to perform remorse. Optimize for the engineer two years from now who hits something similar at 3am.
Procedure
- Timeline first, from artifacts. Build it from logs, alerts, deploy records and chat timestamps — not memory. Every entry: time (with zone), what happened, what was known at that moment. Mark detection, diagnosis, mitigation, resolution.
- Impact, quantified. Who/what/how long/how many: "checkout failed for 12 customers over 3h; all recovered" beats "some users were affected".
- Root cause as a causal chain, not a single line. Use "because" links: webhooks dropped → because the endpoint 500'd on duplicates → because a unique-constraint violation was treated as fatal → because the handler assumed Stripe never retries. The last "because" is usually an assumption, and assumptions are what you fix.
- Blameless mechanically: name systems and decisions, not people. "The deploy script allowed a config-less rollout" — not "X forgot the config". If a person had to be careful for the system to be safe, that's the finding.
- What went well / what got lucky. Luck is a finding too ("we noticed only because someone happened to be watching dashboards").
- Action items that would have prevented or shortened THIS incident, each with an owner and a date. Test each one: "would this have helped on the timeline above?" If not, cut it. 3–5 strong items beat 15 aspirational ones.
Skeleton
# 2026-04-02 — Payments webhook outage (3h, 12 failed checkouts)
**Summary** (3 sentences: what broke, impact, fix)
**Timeline** (timestamped, detection → resolution)
**Root cause** (causal chain, ending at the broken assumption)
**What went well / what got lucky**
**Action items** (owner · due date · "would it have helped?")
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.
- 6d ago First seen · 49 lines · 42 tokens per session scan A 0fccd76ab00b
incident-postmortem is a skill published in the GitHub repository jnMetaCode/skillet (1 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 544 once invoked, about $0.0002 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
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
aomi
Aomi CLI — natural-language to executable on-chain transactions via an agent. Send a prompt like 'swap 1 ETH for USDC' and the agent stages calldata, simulates as a batch, and returns a queued tx for you to sign. Account-abstraction-first signing (EIP-7702 on mainnet, ERC-4337 on L2s) with EOA fallback. Covers swaps…
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
hugging-face-tool-builder
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
incident-response
Incident triage, cascade prevention, and postmortem methodology. Use when handling production incidents, designing resilience patterns, or conducting chaos engineering exercises.