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/florianbruniaux/claude-code-plugins/ci-pipelinenpx skills add FlorianBruniaux/claude-code-plugins --skill ci-pipelinegit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/skills/florianbruniaux/claude-code-plugins/ci-pipeline)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/ci-pipeline"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/ci-pipeline.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00668 |
| Opus 5 | $0.00010 | $0.00334 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
ci-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/ci:pipeline: Push and trigger pipeline
Pushes the current branch and returns the pipeline tracking link.
Process
BRANCH=$(git branch --show-current)
# 1. Safety checks
if echo "$BRANCH" | grep -qE "^(main|master|production)$"; then
echo "❌ Direct push to $BRANCH is not allowed. Create a feature/fix branch."
exit 1
fi
# 2. Check for uncommitted changes
UNCOMMITTED=$(git status --porcelain | wc -l | tr -d ' ')
if [ "$UNCOMMITTED" -gt 0 ]; then
echo "⚠️ $UNCOMMITTED uncommitted file(s):"
git status --short
echo ""
echo "Commit first with /commit or git add + git commit"
exit 0
fi
# 3. Push
echo "Pushing → origin/$BRANCH"
git push origin "$BRANCH" 2>&1
Pipeline URL
GitLab CI
REMOTE=$(git remote get-url origin 2>/dev/null || echo "")
WEB_URL=$(echo "$REMOTE" | sed 's/git@gitlab\.com:/https:\/\/gitlab.com\//' | sed 's/\.git$//')
echo ""
echo "✅ Push OK"
echo " Pipeline: $WEB_URL/-/pipelines?ref=$BRANCH"
# Live status via glab (if installed)
if command -v glab &>/dev/null; then
sleep 3
glab ci status --branch "$BRANCH" 2>/dev/null || true
fi
GitHub Actions
REMOTE=$(git remote get-url origin 2>/dev/null || echo "")
WEB_URL=$(echo "$REMOTE" | sed 's/git@github\.com:/https:\/\/github.com\//' | sed 's/\.git$//')
echo ""
echo "✅ Push OK"
echo " Actions: $WEB_URL/actions?query=branch%3A$BRANCH"
# Live status via gh (if installed)
if command -v gh &>/dev/null; then
sleep 5
gh run list --branch "$BRANCH" --limit 3 2>/dev/null || true
fi
Expected output
Pushing → origin/feat/add-payment-retry
Enumerating objects: 12, done.
...
✅ Push OK
Pipeline: https://gitlab.com/org/my-app/-/pipelines?ref=feat/add-payment-retry
Pipeline status (after 3s):
⏳ lint running
⏸️ test waiting
⏸️ deploy waiting
Usage
/ci:pipeline
Target: $ARGUMENTS
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.
- 4d ago First seen · 98 lines · 21 tokens per session scan A 2f1bd3cf6d17
ci-pipeline is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 668 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan, or when the user says "/squid-implement-night".
squid-review-ci
Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. Output: a CI-validated feature PR. Trigger after /squid-review passes, or when the user says "/squid-review-ci".
sop-deploy
部署 SOP — 強制品質 checklist + pre-deploy 確認,不得跳過任何 checkpoint.
ci-and-branch-protection
How CI gates and GitHub branch protection actually behave on this solo free-tier account — the zero-coverage hole in aggregate jobs, the 403 on private repos, and the three traps that permanently deadlock a solo merge. Load before writing or changing a CI gate, adding a pr-gate caller, or setting/checking branch…
mlops-and-deployment
MLOps and the production ML lifecycle -- model packaging and serving, CI/CD for ML, experiment tracking, model registries, reproducibility, production monitoring for data and concept drift, retraining pipelines, A/B and shadow deployment, and rollback. Covers batch vs online/real-time inference, REST endpoints…
pipeline
Full CI pipeline — typecheck, lint, build, test, security scan, report.