hs-to-rocq: Command for Claude Code

.claude/commands/ci-fix.md

ci-fix is a command for Claude Code from plclub/hs-to-rocq. It costs 44 tokens per session (2,517 once invoked), scanned A, original, MIT.

A command that runs the repository's continuous-integration checks locally, fixes failures, and records the fixes in a log.

In plain words
What is it for?
Use it to check builds, Coq targets, and tests, then commit any required corrections.
Why use it?
It catches build and test problems before code is pushed and keeps a record of what went wrong.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is plclub/hs-to-rocq's own configuration. It tells Claude Code how to work on hs-to-rocq itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hs-to-rocq configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/plclub/hs-to-rocq/master/.claude/commands/ci-fix.md
Clone the repo
git clone --depth 1 https://github.com/plclub/hs-to-rocq

Made for: Claude Code.

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-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/plclub/hs-to-rocq/ci-fix/github.svg)](https://agentmods.dev/commands/plclub/hs-to-rocq/ci-fix)
Your own site
<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.

agentmods 80×15 button for ci-fix

Your own site · 80×15
<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>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,517 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 $0.00044 $0.02517
Opus 5 $0.00022 $0.01259
Sonnet 5 $0.00009 $0.00503
Haiku 4.5 $0.00004 $0.00252

Measured 7d ago against content hash 5c37245b0c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 7d 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.

.claude/commands/ci-fix.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run CI checks locally (mirroring .github/workflows/hs-to-rocq.yml), diagnose and fix any failures, then commit the fixes. All tools (stack, coqc, coq_makefile) are already installed — no Docker or opam setup needed. Do NOT use --allow-different-user (that's only for CI containers).

All commands run from the workspace root using relative paths.

The argument is: $ARGUMENTS

If the argument is empty or "all", run ALL four jobs in order. Otherwise run only the specified job.

Workflow

For each job:

  1. Run the CI step
  2. If it passes, move on
  3. If it fails, diagnose the error, fix it, re-run to verify, then continue
  4. After all jobs pass, commit any changes made during fixing

Keep an intervention log at .claude/ci-fix-log.md documenting each failure and how it was fixed. This helps track what went wrong and why.

Job: build

stack build

If it fails: Read the compiler error carefully. The Haskell source is in src/. Fix the compilation error, re-run stack build to verify.

Job: test-coq

Build all Coq targets in dependency order. For each directory, generate the Makefile from _CoqProject first. Run each group sequentially — they depend on each other in order.

# 1. base + base-thy
(cd base; coq_makefile -f _CoqProject -o Makefile) && make -j -C base
(cd base-thy; coq_makefile -f _CoqProject -o Makefile) && make -j -C base-thy

# 2. containers
(cd examples/containers/lib; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/containers/lib
(cd examples/containers/theories; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/containers/theories

# 3. transformers
(cd examples/transformers/lib; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/transformers/lib

# 4. graph
(cd examples/graph/lib; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/graph/lib
(cd examples/graph/theories; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/graph/theories

# 5. ghc
(cd examples/ghc/lib; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/ghc/lib
(cd examples/ghc/theories; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/ghc/theories

# 6. core-semantics
(cd examples/core-semantics/lib; coq_makefile -f _CoqProject -o Makefile) && make -j -C examples/core-semantics/lib

# 7. resources
coqc -Q base "" examples/resources/list_monad.v

Read the full file on GitHub · 204 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. 7d ago First seen · 204 lines · 44 tokens per session scan A 5c37245b0c46

Subscribe to this mod's changes

ci-fix is a command published in the GitHub repository plclub/hs-to-rocq (96 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 2,517 once invoked, about $0.0002 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 2026-09-01.