ci-routing

ci-routing is a skill for Claude Code from HigorAlves/orc. It costs 70 tokens per session (796 once invoked), scanned A, original, MIT.

A procedure for handling a failed continuous-integration (CI) check, where automated builds and tests run on code changes.

In plain words
What is it for?
Showing a concise CI diagnosis, applying a listed fix and rerunning checks, or recording that more debugging is needed.
Why use it?
It turns a diagnosis into a controlled decision: accept a green result, apply fixes, investigate further, or treat the failure as an infrastructure problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the orc plugin — 80 skills, 30 commands, 14 agents, 5 hooks shipped together

Good fit Showing a concise CI diagnosis, applying a listed fix and rerunning checks, or recording that more debugging is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/higoralves/orc/ci-routing
Install

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.

Any agent
npx skills add HigorAlves/orc --skill ci-routing
Clone the repo
git clone --depth 1 https://github.com/HigorAlves/orc

Made for: Claude Code.

Or install orc, the plugin that ships this one along with the rest of its 80 skills, 30 commands, 14 agents, 5 hooks.

Wrote 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.

agentmods badge for ci-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/higoralves/orc/ci-routing/github.svg)](https://agentmods.dev/skills/higoralves/orc/ci-routing)
Your own site
<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.

agentmods 80×15 button for ci-routing

Your own site · 80×15
<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>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 96cadcf2cee6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

orc/skills/ci-routing/SKILL.md · 50 lines

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 AskUserQuestionone call, two questions (the landing decision is collected up front, so a green fixer report lands without a second stop):

  1. Apply the fix list? — Apply (dispatch orc-code-fixer with the fix list + diagnosis path; it applies edits, runs tests, returns a diff + test summary) / Edit the list first / This needs real debugging (jump to needs-debug) / Abort.
  2. 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

Read the full file on GitHub · 50 lines

Changes

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.

  1. 9d ago First seen · 50 lines · 70 tokens per session scan A 96cadcf2cee6

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories