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 skills add HigorAlves/orc --skill ci-routinggit 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/skills/higoralves/orc/ci-routing)<a href="https://agentmods.dev/skills/higoralves/orc/ci-routing"><img src="https://agentmods.dev/badge/skills/higoralves/orc/ci-routing/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/higoralves/orc/ci-routing"><img src="https://agentmods.dev/badge/skills/higoralves/orc/ci-routing.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 | $0.00070 | $0.00796 |
| Opus 5 | $0.00035 | $0.00398 |
| Sonnet 5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
ci-routing 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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Routing
The single source of truth for acting on an orc-ci-investigator diagnosis — /orc:ci and /orc:flow's post-open CI gate both execute this protocol instead of restating it. Input: the diagnosis (verdict + evidence table + fix list), already saved verbatim to ${ORC_STATE_DIR}/<branch>/files/ci-diagnosis.md.
Single-render rule: the diagnosis is saved via Write — never echoed wholesale into conversation. It gets ONE capped rendering: the fix list + one evidence line per root cause + the file path. Every later step references the saved file; quotes are capped at 3 evidence lines.
green
Say so — one line, run ID cited. Mark the session step complete and stop.
fixable
Render the one preview (> **📋 Preview — CI fix list**: N root causes across M jobs, then the numbered <file>:<line> — <change> — clears <job> list), then AskUserQuestion — one call, two questions (the landing decision is collected up front, so a green fixer report lands without a second stop):
- Apply the fix list? — Apply (dispatch
orc-code-fixerwith the fix list + diagnosis path; it applies edits, runs tests, returns a diff + test summary) / Edit the list first / This needs real debugging (jump toneeds-debug) / Abort. - After a green fixer report, land it how? (ignored unless the fixer ran and came back green) — Commit + push + re-watch (Recommended:
orc:git-commit,git push, re-watch the run until it concludes) / Commit only / Show me the diff first.
Red fixer report → discard the landing answer and return the new evidence to the investigator (it sees the failed attempt) — or offer the needs-debug hand-off. Loop until green or the user explicitly advances with red CI (logged to the digest).
flake
Quote up to 3 run-history evidence lines proving intermittency, then AskUserQuestion: Re-run failed jobs (gh run rerun <id> --failed, then watch) / Re-run everything / Not convinced — treat as fixable or needs-debug / Skip.
infra
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.
- 9d ago First seen · 50 lines · 70 tokens per session scan A 96cadcf2cee6
ci-routing is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 796 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 skills, from other repositories
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
github-ci-fix
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
comet-github-ci-triage
A workflow for diagnosing failed GitHub Actions checks on a Comet pull request. GitHub Actions runs automated builds and tests; a pull request is a proposed code change waiting to be reviewed and merged.