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 agentmods add skills/clima/cloudmicrophysics.jl/fix-cinpx skills add CliMA/CloudMicrophysics.jl --skill fix-cigit clone --depth 1 https://github.com/CliMA/CloudMicrophysics.jlWhat 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 | $0.00084 | $0.04852 |
| Opus 5 | $0.00042 | $0.02426 |
| Sonnet 5 | $0.00017 | $0.00970 |
| Haiku 4.5 | $0.00008 | $0.00485 |
Grade A, and why
fix-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 2d 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.
This is a copy
100% identical to fix-ci — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix CI
The loop:
- At session start: set up CI access (Section 1), verify the local tools (Section 4), and create or re-read the measurement ledger (Section 7).
- Triage every failed job of the latest build — Buildkite
hard_failedsteps and failed GitHub Actions checks (Section 2). After the FIRST complete build of the PR, also run the job-time comparison against main (Section 5.2) — do not wait until correctness work is done. - Fix ONE root cause (Sections 3, 6, 8, 9).
- Verify the fix locally (Section 4).
- If the change is performance-relevant — it touches hot loops, kernels, broadcasting or indexing machinery, type parameters of core structs, or compiler annotations — benchmark against main (Section 5).
- Format, commit, push (Section 2).
- Repeat until CI is green or you reach a decision only the repository owner can make (Section 3).
1. Set up access to CI results before anything else
- GitHub Actions: raw job logs require authentication. Check
gh auth status; ifghis missing or logged out, STOP and ask the user to install and authenticate it (gh auth login). Then:- Statuses:
gh api repos/<org>/<repo>/commits/<sha>/check-runs - Logs:
gh api repos/<org>/<repo>/actions/jobs/<job id>/logs(the check-run id is the job id)
- Statuses:
- Buildkite (CliMA's GPU/MPI CI): public, no auth needed. All endpoints
return JSON with the header
Accept: application/json:- Build state:
https://buildkite.com/<org>/<pipeline>/builds/<N>.json - Steps with outcomes and job ids:
https://buildkite.com/<org>/<pipeline>/builds/<N>/data/steps?exclude_group_steps=true(each step haslabel,outcome—passed/hard_failed/soft_failed—statistics.latest_job_id, andlatest_job_started_at/finished_attimestamps for wall-time comparisons) - Job log:
https://buildkite.com/organizations/<org>/pipelines/<pipeline>/builds/<N>/jobs/<job id>/log(read theoutputfield, strip HTML tags, unescape entities) - Job artifacts (e.g. flame graphs): GET
https://buildkite.com/organizations/<org>/pipelines/<pipeline>/builds/<N>/jobs/<job id>/artifacts, then GET each artifact'surl.
- Build state:
- Map a commit to all of its builds (including extra pipelines like an
end-to-end performance pipeline) via
gh api repos/<org>/<repo>/commits/<sha>/status— each status carries atarget_url. To find a branch's latest build, resolve its head sha first (gh api repos/<org>/<repo>/commits/<branch> --jq .sha).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 356 lines · 84 tokens per session scan A af7d9fb95438
fix-ci is a skill published in the GitHub repository CliMA/CloudMicrophysics.jl (53 stars, last pushed 7d ago), licensed Apache-2.0. It adds 84 tokens to every session and 4,852 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to fix-ci, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
add-cuda-kernel
Step-by-step tutorial for adding new CUDA kernels to FlashInfer.
debug-cuda-crash
Tutorial for debugging CUDA crashes using API logging.
review
Structured PR review for pygraphistry. Input: PR number/branch (default current branch PR). Output: findings and convergence artifacts under plans/ /. Method: multi-wave, evidence-first review across spec, correctness, tests, security, code quality, DRY, concurrency, performance, architecture, operability, and…
test-amplification
Methodical bug-driven test amplification for pygraphistry features. Use when hardening a feature area via user-workflow exploration, 5-Whys retrospectives, bug-taxonomy derivation, concrete test planning, implementation, and safety-gated validation.