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 commands/fusengine/agents/watch-cigit clone --depth 1 https://github.com/fusengine/agentsWhat 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 | $0.00442 |
| Opus 5 | $0.00010 | $0.00221 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
watch-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Watch CI/CD
Monitor and auto-fix CI failures:
-
Get Latest CI Run:
gh run list --limit 1 gh run view [RUN_ID] -
Check Status:
- ✅ Success → Done
- 🔄 In Progress → Wait (sleep 30s, check again)
- ❌ Failed → Proceed to fix
-
Analyze Failures:
gh run view [RUN_ID] --log-failedExtract:
- Which jobs failed
- Error messages
- Stack traces
- File locations
-
Categorize Failures:
- Linter Errors: Run linters locally, fix with sniper
- Test Failures: Identify failing tests, fix logic
- Build Errors: Resolve compilation/build issues
- Dependency Issues: Update/fix package conflicts
-
Apply Fixes: Based on failure type:
-
Use sniper for linter errors
-
Use research-expert for framework-specific issues
- Fix code logic for test failures
- Update dependencies for build issues
-
-
Verify Locally:
bun run lint bun test bun run build -
Commit and Push:
git commit -m "$(cat <<'EOF' fix(ci): Resolve CI pipeline failures - [Fix 1] - [Fix 2] EOF )" git push -
Monitor New Run: Wait for new CI run and repeat if needed.
Arguments:
- $ARGUMENTS can specify specific job to watch
Example Usage:
/watch-ci→ Monitor latest CI run/watch-ci test→ Watch only test jobs
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.
- yesterday First seen · 75 lines · 21 tokens per session scan A 3faadd33974d
watch-ci is a command published in the GitHub repository fusengine/agents (25 stars, last pushed 28d ago), licensed MIT. It adds 21 tokens to every session and 442 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 commands, from other repositories
burn-rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
update-issue
Update an issue description with structured, evidence-backed content.
publish-skill
Sync a marketplace skill to the documentation site. Creates skill detail pages (EN/ZH), updates the marketplace index, and updates docs.json navigation.
deploy
Deploy Solana program (devnet first, then mainnet).
generate-idl-client
Generate TypeScript client from Solana program IDL using Codama or Anchor.