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 oxbshw/LLM-Agents-Ecosystem-Handbook --skill incident-postmortemgit clone --depth 1 https://github.com/oxbshw/LLM-Agents-Ecosystem-HandbookWrote 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/oxbshw/llm-agents-ecosystem-handbook/incident-postmortem)<a href="https://agentmods.dev/skills/oxbshw/llm-agents-ecosystem-handbook/incident-postmortem"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/incident-postmortem/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/oxbshw/llm-agents-ecosystem-handbook/incident-postmortem"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/incident-postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00464 |
| Opus 5.5 | $0.00012 | $0.00186 |
| Sonnet 5.5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 2mo 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
When to use
- After an incident with customer impact
- After a near-miss worth documenting
- For drills / GameDay exercises
When NOT to use
- Live incidents (use
incident-runbookinstead) - Pure private learnings (use a personal log)
Inputs
| Name | Type | Required | Notes |
|---|---|---|---|
timeline |
text or paths | yes | Source notes, alert links, chat extracts |
severity |
S0–S3 |
yes | Severity at peak |
incident_id |
string | yes | e.g. INC-2026-04-12-001 |
Outputs
postmortem.md with: Summary, Impact, Timeline, Direct cause, Contributing factors, What went well, What didn't, Action items.
Workflow
- Reconstruct the timeline (UTC), one row per notable event
- State impact in user-facing terms (requests failed, dollars lost, customers affected)
- Identify the direct cause in one sentence — what specifically broke
- List contributing factors (the conditions that made the incident possible / hard to mitigate)
- Separate what went well (genuine wins, not platitudes) and what didn't
- Owners + dates on every action item; hard fail if missing
- Tone: blameless. Describe systems failing, not people.
References
Success criteria
- Every action item has an owner and a date
- Direct cause is one sentence
- No names attached to fault; only roles / systems
- Timeline times in UTC
Failure modes
- Missing source data → list gaps explicitly; don't fill with guesses
- Conflicting timelines → record both, flag for review
What ships with it
1 file 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.
- 2mo ago First seen · 52 lines · 30 tokens per session scan A 5d84fff91b5c
incident-postmortem is a skill published in the GitHub repository oxbshw/LLM-Agents-Ecosystem-Handbook (558 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 464 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
incident-postmortem compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| incident-postmortemoxbshw/LLM-Agents-Ecosystem-Handbook | Skill | 558 | 4mo ago | MIT | A | 30 | Claude Code, Codex |
| alert-sopPM-Shawn/Abu-Cowork | Skill | 419 | 2d ago | Apache-2.0 | A | 20 | Claude Code |
| lastlight-debugnearform/lastlight | Skill | 44 | 2d ago | MIT | A | 138 | Claude Code |
| debug-productionnearform/lastlight | Skill | 44 | 2d ago | MIT | A | 66 | Claude Code, Codex |
| structured-logging-and-observabilityaiming-lab/MetaClaw | Skill | 3.5k | 5mo ago | MIT | A | 46 | Claude Code, Codex |
| robust-error-handling-in-scriptsaiming-lab/MetaClaw | Skill | 3.5k | 5mo ago | MIT | A | 40 | Claude Code, Codex |
| tinker-debuggvkhosla/pi-tinker | Skill | 25 | yesterday | Apache-2.0 | A | 52 | Claude Code |