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 johnqtcg/awesome-skills --skill incident-postmortemgit clone --depth 1 https://github.com/johnqtcg/awesome-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/johnqtcg/awesome-skills/incident-postmortem)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/incident-postmortem"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/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/johnqtcg/awesome-skills/incident-postmortem"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/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 | $0.00098 | $0.05682 |
| Opus 5 | $0.00049 | $0.02841 |
| Sonnet 5 | $0.00020 | $0.01136 |
| Haiku 4.5 | $0.00010 | $0.00568 |
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 12d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Reference
| When you need... | Jump to |
|---|---|
| Write a post-mortem from scratch | §2 Gates -> §5 Checklist -> §9 Output |
| Extract timeline from logs/events | §5.1 Timeline Construction |
| Perform root cause analysis | §5.2 Root Cause Analysis |
| Classify incident severity | §6 Severity Classification |
| Generate action items | §5.4 Action Items |
| Review an existing post-mortem | §2 Gates -> §5 Checklist -> §8 Scorecard |
| Know which sections your output needs | §9.0 Required Sections by Mode |
| Redact before sharing / set distribution | §2 Gate 5 Sensitive Data & Distribution |
| Choose an RCA technique other than 5-Why | §5.2 item 5 -> rca-techniques.md §0 |
1 Scope
In scope: blameless post-mortem writing, timeline extraction from logs/alerts/chat/ monitoring, root cause analysis (5-Why, fishbone, fault tree), severity classification, action items with ownership and deadlines, contributing-factor identification, detection/response gap analysis, post-mortem review and quality scoring.
Out of scope: live incident response / on-call procedures (use runbooks), debugging
code to find the root cause (use systematic-debugging), monitoring setup (use
monitoring-alerting), infrastructure provisioning, customer communication drafting
(PR/comms team scope).
Language: write the post-mortem in the language the user is using. The linter's
section, source, owner/deadline, category and N/A patterns are bilingual (English and
Chinese, including full-width （） and ：), so a Chinese post-mortem passes the same
gates. Other languages are not yet aliased — a German or Japanese document will be
mis-reported as missing sections; lint it in English or add the aliases first.
What ships with it
40 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.
- references/postmortem-template.md 13 KB
- references/rca-techniques.md 9.4 KB
- references/severity-framework.md 6.0 KB
- scripts/grade_postmortem_eval.py 12 KB runs code
- scripts/lint_postmortem.py 30 KB runs code
- scripts/run_live_eval.sh 6.8 KB runs code
- scripts/run_regression.sh 537 B runs code
- scripts/summarize_eval.py 4.7 KB runs code
- scripts/tests/COVERAGE.md 21 KB
- scripts/tests/eval/results/README.md 2.2 KB
- scripts/tests/eval/scenario_and_gated_failure.json 1.1 KB
- scripts/tests/eval/scenario_chinese_incident.json 1.2 KB
- scripts/tests/eval/scenario_full_draft.json 1.4 KB
- scripts/tests/eval/scenario_no_incident.json 796 B
- scripts/tests/eval/scenario_pinned_file_artifact.json 1.0 KB
- scripts/tests/eval/scenario_quick_timeline.json 1.1 KB
- scripts/tests/eval/scenario_review_existing.json 1.2 KB
- scripts/tests/eval/scenario_secrets_in_evidence.json 979 B
- scripts/tests/eval/scenario_strict_single_section.json 1.7 KB
- scripts/tests/eval/scenario_verbal_only.json 950 B
- scripts/tests/golden/001_blame_language.json 1.0 KB
- scripts/tests/golden/002_unsourced_timeline.json 951 B
- scripts/tests/golden/003_unowned_actions.json 981 B
- scripts/tests/golden/004_shallow_rca.json 973 B
- scripts/tests/golden/005_no_impact_metrics.json 969 B
- scripts/tests/golden/006_missing_what_went_well.json 989 B
- scripts/tests/golden/007_no_tracking.json 1.0 KB
- scripts/tests/golden/008_good_postmortem.json 4.0 KB
- scripts/tests/golden/009_good_rca.json 1.4 KB
- scripts/tests/golden/010_degraded_verbal.json 992 B
- scripts/tests/golden/011_degraded_no_incident.json 823 B
- scripts/tests/golden/012_workflow_full_draft.json 1.0 KB
- scripts/tests/golden/013_workflow_review.json 1019 B
- scripts/tests/golden/014_recurring_incident.json 2.4 KB
- scripts/tests/golden/015_cross_team_sev1.json 1.6 KB
- scripts/tests/golden/016_near_miss_analysis.json 1.6 KB
- scripts/tests/test_forward_eval.py 37 KB runs code
- scripts/tests/test_golden_scenarios.py 20 KB runs code
- scripts/tests/test_lint_postmortem.py 43 KB runs code
- scripts/tests/test_skill_contract.py 31 KB runs code
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.
- 12d ago First seen · 487 lines · 98 tokens per session scan A 4c5ae8033c9e
incident-postmortem is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 5,682 once invoked, about $0.0005 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
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.