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 agentmods add commands/higoralves/orc/incidentgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/incident)<a href="https://agentmods.dev/commands/higoralves/orc/incident"><img src="https://agentmods.dev/badge/commands/higoralves/orc/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 | $0.00054 | $0.02848 |
| Opus 5 | $0.00027 | $0.01424 |
| Sonnet 5 | $0.00011 | $0.00570 |
| Haiku 4.5 | $0.00005 | $0.00285 |
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 5d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:incident
The during-the-fire half of incident handling. /orc:postmortem learns from an incident after it's over; /orc:incident runs one while it's happening: triage evidence, size the blast radius, choose mitigate-first or root-cause-first, and keep a timestamped timeline that becomes the postmortem's spine. Stop the bleeding before you study the wound.
Arguments
- First argument (free-form) — one of:
- A Sentry issue short ID (e.g.
PROJ-123) or issue URL — pulled live via theorc:sentry-cliskill. - A pasted stack trace.
- A described symptom ("checkout is 500ing since the 14:00 deploy").
- A Sentry issue short ID (e.g.
--severity sev-1|sev-2|sev-3— optional. Skips the severity proposal in Phase 2 (blast radius is still assessed).
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection). loose context → surface and stop (no state dir to write).
Phase 1 — Intake + timeline start
- Determine the current branch:
git branch --show-current. Sanitize (/→-). Create${ORC_STATE_DIR}/<sanitized-branch>/files/incident/. - Register state:
orc-state init --command incident --total-phases 5. Defer toorc:state-protocolfor schema and rules. - Start the timeline. Create
${ORC_STATE_DIR}/<sanitized-branch>/files/incident/timeline.md:
# Incident timeline — <slug>
Append-only. One line per action or finding, UTC.
| Time (UTC) | Who | What |
|---|---|---|
| <date -u +%Y-%m-%dT%H:%M:%SZ> | orc | Incident session opened; intake: <sentry issue \| stack trace \| symptom> |
Every subsequent action or finding in ANY phase appends a row (date -u +%Y-%m-%dT%H:%M:%SZ for timestamps). This is an iron rule, not a suggestion — the timeline is what /orc:postmortem inherits.
- Classify the input and gather evidence:
- Sentry issue ID/URL → invoke the
orc:sentry-cliskill (read itsreferences/agent-guidance.mdfirst, thenreferences/issue.md/references/event.mdas needed). Just run the commands — the CLI auto-handles auth and org/project detection:
- Sentry issue ID/URL → invoke the
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.
- 5d ago First seen · 174 lines · 54 tokens per session scan A 0ab5f2a017e6
incident is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 2,848 once invoked, about $0.0003 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 commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
uninstall
Remove flow-next files from project.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.