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/postmortemgit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00040 | $0.01549 |
| Opus 5 | $0.00020 | $0.00775 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:postmortem
Capture what happened, why it happened, and what changes to prevent recurrence.
Arguments
<short-slug>— optional. Brief incident identifier (e.g.db-failover-2026-05-01). Prompts if omitted.--severity sev-1|sev-2|sev-3— optional. If omitted, the workflow proposes a tier and confirms with the user.
Workflow
Phase 1 — Gate
Invoke orc:postmortem-writing. Confirm a postmortem is warranted:
- customer-visible incident, OR
- an on-call page fired, OR
- near-miss with a real defect, OR
- recurrence of the same incident type.
If borderline (e.g. caught in CI, no production impact), print the Gate headline (**⛔ Gate — postmortem-worthy?**, per orc:callouts), then AskUserQuestion:
- "Write a full postmortem anyway"
- "Write a one-paragraph near-miss note instead (no full template)"
- "Skip — caught early, no learning to capture"
Phase 2 — Establish severity
If no --severity flag: propose a tier based on user description and confirm via AskUserQuestion:
- SEV-1: total outage / data loss / security event
- SEV-2: significant degradation / partial outage
- SEV-3: edge-case impact / near-miss
If the project doesn't have severity definitions, note this — surface a suggestion to author them as an ADR / policy doc afterward.
Phase 3 — Initialize workspace
Register state: orc-state init --command postmortem --total-phases 7, then orc-state phase set 3 --label "severity-<tier>". Defer to orc:state-protocol for schema and rules.
Decide where the document lives via AskUserQuestion:
- "In-repo at
docs/postmortems/YYYY-MM-DD-<slug>.md" - "Shared doc tool (Notion / Confluence / Google Doc) — author in
.orc/first; you'll mirror it manually"
Phase 4 — Build the timeline FIRST
The timeline is the spine; everything else depends on it. Walk the user through:
- Detection (what fired, who saw it, when).
- Response (who ack'd, what they checked first, key dashboard URLs).
- Mitigation (what change actually stopped the bleeding).
- Resolution (when traffic / metrics returned to baseline).
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.
- 2d ago First seen · 138 lines · 40 tokens per session scan A 633f71975c6e
postmortem is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 1,549 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 2026-08-31.
Other commands, from other repositories
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
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.
get-flow-run
Inspect a Postman Flow run by its Run ID — per-block logs, failing block, and status.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…