A CI diagnosis and repair command for failed automated checks. CI, or continuous integration, runs builds and tests whenever code is pushed or a pull request is updated.

Use it after failed pull-request checks or a push, optionally watch a running CI job, investigate a chosen run, and apply an automated fix when the failure is caused by code.

It explains why a CI run is red using evidence from its logs and routes the problem toward a code fix, retry, infrastructure escalation, or debugging session.

ci — Command for Claude Code by HigorAlves/orc

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.

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 87 skills, 29 commands, 14 agents, 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/higoralves/orc/ci/github.svg)](https://agentmods.dev/commands/higoralves/orc/ci)

Your own site

<a href="https://agentmods.dev/commands/higoralves/orc/ci"><img src="https://agentmods.dev/badge/commands/higoralves/orc/ci/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/higoralves/orc/ci"><img src="https://agentmods.dev/badge/commands/higoralves/orc/ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,411 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01411
Opus 5.5	$0.00019	$0.00564
Sonnet 5.5	$0.00010	$0.00282
Haiku 4.5	$0.00005	$0.00141

Measured today against content hash eacb3c0498d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 today.

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/commands/ci.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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 (overrides interaction_policy); ladder and hard-outward exemption in orc:gates §6.
<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: poll gh run watch <id> (or gh 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 via gh pr list --head <branch>.
--watch: start gh run watch <id> --exit-status for the newest run on the ref (or gh pr checks <pr> --watch when the ref is a PR) in the background — Bash with run_in_background: true, or the Monitor tool when available — so the session stays responsive; say so in one line and end the turn. You're re-invoked when it exits. 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 via orc-state digest write -. Defer to orc:state-protocol for schema and rules. (If an in-progress session already exists for this branch — e.g. a flow — do NOT re-init as ci; append a ci_status line to that session's checkpoint body instead.)

Read the full file on GitHub · 86 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.

today Changed · +1 lines · -19 tokens per session eacb3c0498d6
15d ago Changed 4a397f8c147b
1mo ago First seen · 85 lines · 67 tokens per session scan A e81fcb8b88ca

Subscribe to this mod's changes

ci is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,411 once invoked, about $0.0002 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 2026-08-31.

CI and CD Claude Code Debugging DevOps and cloud agentic-coding ai-agents anthropic claude claude-code-plugin

ci

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/orc:ci

Arguments

Workflow

Phase 0 — Detect context

Phase 1 — Resolve the ref + run

What this file has done since we first saw it

Other commands, from other repositories

pr-ci-fix

parallax-status

ccc-makeover

ccc-debug-session

diagnose

incident-response