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 ckorhonen/swe-skills --skill incident-followup-auditgit clone --depth 1 https://github.com/ckorhonen/swe-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/ckorhonen/swe-skills/incident-followup-audit)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/incident-followup-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/incident-followup-audit/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/ckorhonen/swe-skills/incident-followup-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/incident-followup-audit.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 | $0.00109 | $0.01260 |
| Opus 5 | $0.00055 | $0.00630 |
| Sonnet 5 | $0.00022 | $0.00252 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
swe:incident-followup-audit 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Incident Follow-up Audit
What This Skill Does
Use this skill to check whether the engineering work that should happen after an incident actually happened.
The goal is not to explain the incident itself. The goal is to answer:
- What follow-up work is done
- What follow-up work is missing
- What follow-up work is still uncertain
- What remains in the smallest sensible backlog
The skill should stay evidence-led and conservative. If follow-up cannot be proven, mark it as unknown rather than filling in the gap.
When To Use
Use this skill when the user wants to:
- Audit postmortem follow-through after a sev or production incident
- Check whether regression tests, monitors, runbooks, or docs were added
- See whether ownership, tickets, or rollback learnings were captured
- Review what is still left to do before the incident can be considered fully closed
Do Not Use
Do not use this skill for:
- Live incident response or war-room triage
- Root-cause analysis of the incident itself
- Generic code review or bug hunting with no incident context
- Broad cleanup work that is not tied to a concrete incident or postmortem
Inputs To Confirm
Confirm or infer:
- The incident, sev, or postmortem identifier
- The affected service, repo, or time window
- Which source-of-truth artifacts exist
- Whether the user wants a report-only audit or a follow-up backlog
- Which environments or systems can be checked for evidence
If the incident scope is unclear, ask for the narrowest identifier needed to anchor the audit.
Tooling Stance
This skill is tool agnostic.
Use whichever sources provide the strongest direct evidence, such as:
- Postmortems or incident docs
- Issue trackers
- Pull requests and commit history
- CI and test results
- Monitoring, alerting, dashboards, or traces
- Runbooks or operational docs
Prefer direct evidence over inference. If a system is unavailable, say so explicitly.
Instructions
Step 1: Define The Incident Scope
Anchor the audit in a specific incident or sev.
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 · 199 lines · 109 tokens per session scan A 0f21ac2cd3ec
swe:incident-followup-audit is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,260 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 2026-08-31.
Other skills, from other repositories
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
ai-diagnostic
A diagnostic framework that examines a problem across technology, processes, people, and business causes.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
launchworthy
Production readiness audit that turns a demo into a real product. Built for apps shipped fast with AI coding tools (Lovable, Bolt, v0, Cursor, Claude Code). Auto-detects your stack and audits 5 domains (Frontend, Backend & Data, Auth & Security, Infrastructure, Operations), then produces a scored scorecard and a…
azure-mcp-observability
The read-only observability half of the azure-mcp connector — the monitor, resourcehealth, applens, and advisor namespaces: Azure Monitor metrics, Log Analytics KQL, alert-rule state, platform health states, AppLens detectors, and Advisor recommendation categories, plus the degraded-resource investigation order.