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/cigit 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 | $0.00067 | $0.01414 |
| Opus 5 | $0.00034 | $0.00707 |
| Sonnet 5 | $0.00013 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
ci 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:ci
CI is red and you want to know why — and, when it's the code's fault, get it fixed without hand-reading 4,000 lines of logs. /orc:ci dispatches orc-ci-investigator for an evidence-cited diagnosis, then routes on the verdict: fix, re-run, escalate, or hand off to /orc:debug.
Arguments
-
--auto[=guided|full]— autopilot level for this run (overridesinteraction_policy; taxonomy inorc:using-orc). Soft-inward gates consult the resolved policy —guidedauto-advances mechanical confirms with a printed one-liner;fullpre-approves them from settled decisions (orc:state-protocol), stopping only on escalation-only conditions. Hard-outward gates are unaffected at every level. -
<pr-number>or<branch>— optional ref. Omitted → the current branch (and its PR, if one exists). -
--run <id>— pin the investigation to an explicit run ID instead of resolving the newest run for the ref. -
--watch— after a push: pollgh run watch <id>(orgh pr checks <pr> --watch) until the run concludes, then run the normal flow if red. Green → report and exit.
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 repo, no CI to inspect).
In workspace mode, read ${ORC_STATE_DIR}/orc.json for the in-progress session's linkedPRs. With 2+ linked PRs and no explicit ref, AskUserQuestion: investigate all N / pick one / cancel. Iron rule: no silent broadcast. Each targeted PR gets its own investigator dispatch in Phase 2 (parallel, single response, multiple Task calls).
Phase 1 — Resolve the ref + run
- Resolution order:
--run <id>wins; else the explicit<pr-number>/<branch>argument; else the current branch (git branch --show-current) and its PR viagh pr list --head <branch>. --watch: rungh run watch <id>for the newest run on the ref (orgh pr checks <pr> --watchwhen the ref is a PR) and wait for the conclusion. Success → echo the green summary and stop. Failure → continue with that run pinned.- Without
--watch:gh run list --branch <branch> --limit 5/gh pr checks <pr>for a quick read. Everything green → say so and stop — never manufacture work. - Register state:
orc-state init --command ci --total-phases 4, then record the resolved ref + run ID viaorc-state digest write -. Defer toorc:state-protocolfor schema and rules. (If an in-progress session already exists for this branch — e.g. a flow — do NOT re-init asci; append aci_statusline to that session's checkpoint body instead.)
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 · 85 lines · 67 tokens per session scan A e81fcb8b88ca
ci is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,414 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
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…