Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/studioKjm/ai-harness-templatenpx agentmods add commands/studiokjm/ai-harness-template/incidentWrote 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/commands/studiokjm/ai-harness-template/incident)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/incident"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/incident.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 | $0.00022 | $0.01541 |
| Opus 5 | $0.00011 | $0.00771 |
| Sonnet 5 | $0.00004 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
incident 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/incident — Manage Incident Records
"What system allowed this?" — not "who did it?"
When to use
- Production incident detected (alert fired, user-reported, or self-discovered)
- Want to capture timeline + root cause + action items in a durable format
- Avoid the "fixed in Slack and forgot" anti-pattern
Usage
/incident new <slug> --title "..." --severity sev1|sev2|sev3|sev4 [--reporter NAME]
/incident list [--status ...] [--severity sev1|sev2|sev3|sev4]
/incident show <incident-id>
/incident timeline add <id> --time TIME --event "..." [--source SRC]
/incident analyze <id> # recording → analyzing
/incident publish <id> # analyzing → published (requires blameless review)
/incident close <id> # published → acted-on (all action items resolved)
/incident archive <id> # acted-on → archived
For action items see /incident-action. For pattern analysis see /incident-patterns.
Prerequisites
None. Incident review can run any time, even before any other methodology.
Severity guide
| Sev | Meaning | Response time |
|---|---|---|
| sev1 | Total outage / data loss / security breach | < 1 hour |
| sev2 | Major degradation (significant subset broken) | < 4 hours |
| sev3 | Partial degradation (specific feature/segment) | Same day |
| sev4 | Minor / cosmetic | Next day |
State machine
[recording] → [analyzing] → [published] → [acted-on] → [archived]
| State | Meaning | Move to next when |
|---|---|---|
| recording | Timeline being captured, response active or just ended | Response done, ready to investigate |
| analyzing | Root cause investigation (5-whys, contributing factors) | Postmortem doc written, blameless review passed |
| published | Postmortem distributed to stakeholders | All action items resolved (done/dropped/converted) |
| acted-on | All action items closed | After ~6 months (or manual archive) |
| archived | Historical record only | (terminal) |
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.
- 8d ago First seen · 165 lines · 22 tokens per session scan A faf6fe097f02
incident is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,541 once invoked, about $0.0001 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 commands, from other repositories
capture-feedback
Quick feedback capture with structured signals.
show-lessons
Display promoted lessons and their corrective actions.
harness-review
Review the current change set from an opposing harness-engineering perspective.
harness-doctor
Run Harness Doctor to evaluate how ready the current repository is for reliable AI coding agent collaboration.
harness-update
Update a target repository's harness from the latest harness-starter-kit reference material.
harness-refresh
Refresh a target repository's existing harness by reviewing whether its agent-facing rules, knowledge store, and drift checks are still accurate.