leanspec: Skill for Claude Code

.claude/skills/watch-ci/SKILL.md

watch-ci is a skill for Claude Code from codervisor/leanspec. It costs 25 tokens per session (822 once invoked), scanned A, original, MIT.

A workflow for monitoring GitHub Actions, GitHub's service for running automated builds and tests, after a commit is pushed. It waits for the checks for the current commit to finish and reports their results.

In plain words
What is it for?
Use it after pushing changes to find the matching workflow run, monitor its jobs, and inspect the final CI result for the current commit.
Why use it?
It helps you know whether the exact pushed commit passed its automated checks without repeatedly checking by hand. It also distinguishes unfinished checks from completed failures or successes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is codervisor/leanspec's own configuration. It tells Claude Code how to work on leanspec 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 leanspec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to codervisor/leanspec. 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/codervisor/leanspec/main/.claude/skills/watch-ci/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/codervisor/leanspec

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 watch-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/codervisor/leanspec/watch-ci/github.svg)](https://agentmods.dev/skills/codervisor/leanspec/watch-ci)
Your own site
<a href="https://agentmods.dev/skills/codervisor/leanspec/watch-ci"><img src="https://agentmods.dev/badge/skills/codervisor/leanspec/watch-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.

agentmods 80×15 button for watch-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/codervisor/leanspec/watch-ci"><img src="https://agentmods.dev/badge/skills/codervisor/leanspec/watch-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 30
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 45
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 58
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • low Supply Chain · line 29
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • low Supply Chain · line 44
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • low Supply Chain · line 57
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
How audits are shown
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 $0.00025 $0.00822
Opus 5.5 $0.00010 $0.00329
Sonnet 5.5 $0.00005 $0.00164
Haiku 4.5 $0.00003 $0.00082

Measured 2mo ago against content hash 2b5dc6a3b1b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

watch-ci scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The `gh` CLI is **not available** in the Claude VM. Use the GitHub REST API via `curl`.
.claude/skills/watch-ci/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch CI

Poll the GitHub Actions CI pipeline for the current HEAD commit until all jobs finish.

Environment

The gh CLI is not available in the Claude VM. Use the GitHub REST API via curl. The repo is codervisor/leanspec.

Steps

  1. Get the current commit SHA and branch:

    SHA=$(git rev-parse HEAD)
    BRANCH=$(git branch --show-current)
    echo "Watching CI for commit $SHA on branch $BRANCH"
    
  2. Find the workflow run matching our exact commit. The API returns runs newest-first; filter by head_sha. If the run hasn't appeared yet (GitHub can take a few seconds), retry up to 5 times with 10s waits:

    curl -sH "Accept: application/vnd.github+json" \
      "https://api.github.com/repos/codervisor/lean-spec/actions/runs?branch=$BRANCH&head_sha=$SHA&per_page=1" \
      | python3 -c "
    import json, sys
    data = json.load(sys.stdin)
    runs = data.get('workflow_runs', [])
    if not runs:
        print('NO_RUNS'); sys.exit()
    r = runs[0]
    print(f'RUN_ID={r[\"id\"]}')
    print(f'Status: {r[\"status\"]}  Conclusion: {r.get(\"conclusion\") or \"pending\"}  Commit: {r[\"head_sha\"][:8]}')"
    
  3. Poll jobs until all complete (every 60s for Rust builds which take ~8-10 min):

    curl -sH "Accept: application/vnd.github+json" \
      "https://api.github.com/repos/codervisor/lean-spec/actions/runs/$RUN_ID/jobs" \
      | python3 -c "
    import json, sys
    data = json.load(sys.stdin)
    for j in data.get('jobs', []):
        steps = [s for s in j.get('steps', []) if s['status'] == 'in_progress']
        step_info = f' -> {steps[0][\"name\"]}' if steps else ''
        print(f'{j[\"name\"]:40}  {j[\"status\"]:12}  {j.get(\"conclusion\") or \"\"}{step_info}')"
    
  4. On failure, fetch the failed job logs to diagnose:

    curl -sH "Accept: application/vnd.github+json" \
      "https://api.github.com/repos/codervisor/lean-spec/actions/runs/$RUN_ID/jobs" \
      | python3 -c "
    import json, sys
    data = json.load(sys.stdin)
    for j in data.get('jobs', []):
        if j.get('conclusion') == 'failure':
            print(f'FAILED: {j[\"name\"]} (id: {j[\"id\"]})')
            for s in j.get('steps', []):
                if s.get('conclusion') == 'failure':
                    print(f'  Step: {s[\"name\"]}')"
    

Read the full file on GitHub · 81 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. 2mo ago First seen · 81 lines · 25 tokens per session scan A 2b5dc6a3b1b2

Subscribe to this mod's changes

watch-ci is a skill published in the GitHub repository codervisor/leanspec (300 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 822 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

watch-ci compared with skills from other repositories

watch-ci next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
watch-cicodervisor/leanspecSkill3005mo agoMITA25Claude Code
shipping-and-launchloiane/specs-driven-development-spring-angularSkill62yesterdayMITA64Claude Code
aiox-devopsSynkraAI/aiox-coreSkill3.1kyesterdaynoneA51Claude Code
aiox-devopsSynkraAI/aiox-coreSkill3.1kyesterdaynoneA41Codex
setup-repofiratcand/forgeSkill143mo agoMITA31Claude Code, Codex
github-managerchainlesschain/chainlesschainSkill11todaynoneA21Claude Code
deployment-patternsaffaan-m/ECCSkill298k4d agoMITA41Claude Code, Kiro