Borrowing it
Nothing to install: this file belongs to c9r-io/orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/.claude/skills/ops/SKILL.mdgit clone --depth 1 https://github.com/c9r-io/orchestratorWrote 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/c9r-io/orchestrator/ops)<a href="https://agentmods.dev/skills/c9r-io/orchestrator/ops"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/ops/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/c9r-io/orchestrator/ops"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/ops.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 | $0.00035 | $0.00469 |
| Opus 5.5 | $0.00014 | $0.00188 |
| Sonnet 5.5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
ops 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 2mo 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.
What it actually says
Operations
Discover the runtime contract before acting. In this repository the default operational surface is a host-running orchestratord daemon, not Docker Compose or Kubernetes.
Agent Orchestrator Triage
-
Inspect repository and daemon state:
git status --short orchestrator daemon status orchestrator debug --component daemon -
Inspect task state and bounded logs:
orchestrator task list orchestrator task logs <task-id> -n 200 -
The default runtime root is
~/.orchestratord/; respectORCHESTRATORD_DATA_DIRwhen it is set. Prefer CLI queries over reading SQLite or killing a PID directly. -
For source failures, run the narrowest relevant test first, then broaden to
cargo test --workspace. -
For Web UI failures, use scripts from
gui/package.json, normallynpm testornpm run test:e2efromgui/. -
Use
orchestrator daemon stopfor a graceful stop. Restart only when the user asked for a state-changing operational action.
Optional Container or Cluster Branch
Use Docker Compose only when a compose file exists in the target repository. Use Kubernetes only when a manifest or kustomization tree exists and the user has placed that cluster in scope. When neither exists, mark those checks not applicable instead of substituting assets from project-bootstrap.
For an applicable generated project, the conventional files are docker/docker-compose.yml, scripts/reset-docker.sh, and k8s/base/. Confirm each exact path before running it.
Evidence and Guardrails
- Collect status, the smallest relevant log tail, and a health or CLI check.
- Never delete the daemon database or runtime directory during routine triage.
- Never send an unscoped signal from a stale PID file.
- Do not restart every service when one bounded component is failing.
- Report the failing command, exit code, and relevant evidence rather than claiming recovery from process existence alone.
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.
- 2mo ago First seen · 45 lines · 35 tokens per session scan A 9336d3438277
ops is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 469 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
fix
Diagnose and fix a bug in an isolated git worktree with reproduce-first, test-first methodology.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
rust-check
Run cargo check on the current Rust project to find compile errors.