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 | $0.00015 | $0.00232 |
| Sonnet 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 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.
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.
- 10d 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 (546 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 464 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 2026-08-30.
Other skills, from other repositories
structured-logging-and-observability
Use this skill when building production services, pipelines, or automation that needs to be debugged, monitored, or audited. Add structured logs, metrics, and health checks before shipping any service.
robust-error-handling-in-scripts
Use this skill when writing shell scripts, Python automation, or any unattended batch job. Ensure failures are detected, logged, and handled — never silently ignored.
debug-systematically
Use this skill when diagnosing a bug, unexpected behavior, test failure, or any situation where code does not behave as expected. Follow a structured debugging process instead of randomly changing code.
do-not-retry-without-diagnosis
Common mistake — retrying the same failing command or API call without understanding why it failed. Always diagnose the root cause before retrying anything.
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
lastlight-debug
Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…