Borrowing it
Nothing to install: this file belongs to plclub/hs-to-rocq. 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/plclub/hs-to-rocq/master/.claude/commands/ci-fix.mdgit clone --depth 1 https://github.com/plclub/hs-to-rocqWrote 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/commands/plclub/hs-to-rocq/ci-fix)<a href="https://agentmods.dev/commands/plclub/hs-to-rocq/ci-fix"><img src="https://agentmods.dev/badge/commands/plclub/hs-to-rocq/ci-fix/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/commands/plclub/hs-to-rocq/ci-fix"><img src="https://agentmods.dev/badge/commands/plclub/hs-to-rocq/ci-fix.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 | $0.00015 | $0.02009 |
| Opus 5.5 | $0.00006 | $0.00804 |
| Sonnet 5.5 | $0.00003 | $0.00402 |
| Haiku 4.5 | $0.00002 | $0.00201 |
Grade A, and why
ci-fix 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run local CI checks, repair failures, and commit the verified fixes. Read .claude/commands/ci.md first. It is the authoritative catalog for job selection, prerequisites, per-job compiler environments, executable steps, and result criteria. Also read the root CLAUDE.md for translation and proof conventions. This document adds repair guidance, not a second command catalog.
The argument is: $ARGUMENTS
Apply ci.md, "Select jobs", to this argument. Empty or all means all seven workflow jobs, including HLint, the catalog/direct/harness/concurrency checks in build-haskell, and both Rocq jobs. Use the exact blocks under the corresponding Job: headings, with their prerequisite checks and environment wrappers.
Repair loop
- Complete
ci.md, "Verify prerequisites and protect local work". Record pre-existing changes so repairs do not overwrite or commit user work. - Run each selected job. On failure, capture the command, exit status, toolchain, and diagnostic before editing. Missing tools or unsafe regeneration are blockers, not source-code defects.
- Find the cause using the guidance below. Fix the source of the problem rather than weakening a check. Defer design changes to the user.
- Rerun the smallest relevant check, then the full failed job from
ci.md. Recheck downstream jobs affected by the fix. A translator or shared-rule change requires both compiler suites as well asbuild-haskell; a base change requires its dependent libraries and proofs. - After the last fix, verify the selected jobs against that source state. Record failures, causes, fixes, and verification in
.claude/ci-fix-log.md, preserving existing entries. Finish with the summary and commit steps below.
HLint and Haskell failures
For HLint, first confirm the version from ci.md; do not suppress a finding merely to pass. For compilation errors, inspect the reported source under src/, rebuild, then rerun the remaining build-haskell checks.
For catalog failures, compare ci.md with the current workflow and inspect examples/tests/checks/CiCatalog.hs. Keep the job headings and selection table synchronized, retain the shared-catalog delegation here, and preserve nonzero exits. Rerun the catalog check from ci.md after a repair.
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 · -127 lines · -29 tokens per session 980e13410ee6
- 1mo ago First seen · 204 lines · 44 tokens per session scan A 5c37245b0c46
ci-fix is a command published in the GitHub repository plclub/hs-to-rocq (96 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 2,009 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 2026-09-01.
Other commands, from other repositories
verify
A verification command for FluxDown changes. It runs the checks required by the project, such as formatting, linting changed lines, crate checks, focused tests, image contracts, and CI path checks.
judge-ci-red
Load when: loom-daemon forge wait-checks printed LOOM-CHECKS-RED, or post-verdict.sh … approved exited 6, and a CI-failing verdict is next.
write-test-plan
Generate or update change test plan.
check-fix
Execute quality gates, fix any issues found, and create a single high-quality Conventional Commit summarizing all changes made.
test-setup
Scaffold test framework and CI pipeline.
harness:cicd-fleet
Autonomous CI/CD-remediation orchestrator — triage the red CI/CD-run and flaky-test backlog by cause, fan out worktree-isolated subagents that run the real deflake/heal pipeline, independently verify each fix by artifact and deterministic all-OS CI, and hand back a batch of remediation PRs for one bulk human review.…