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/petarzarkov/dunx/ci-checkgit clone --depth 1 https://github.com/petarzarkov/dunxWrote 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/commands/petarzarkov/dunx/ci-check)<a href="https://agentmods.dev/commands/petarzarkov/dunx/ci-check"><img src="https://agentmods.dev/badge/commands/petarzarkov/dunx/ci-check.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 5.1 | $0.00000 | $0.00268 |
| Opus 5 | $0.00000 | $0.00134 |
| Sonnet 5 | $0.00000 | $0.00054 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
ci-check 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 5d 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
Run every CI gate with one command.
bun run ci
That is scripts/ci.ts. It builds first, then runs the static, unit,
examples, docs and coverage phases at the same time, which is what the jobs
in .github/workflows/ci.yml run and in the same commands. scripts/ci.test.ts
fails if the two ever drift apart.
Each step's output is captured and printed only when that step fails, so read the
summary at the end: it counts the steps, names every failure and prints its
output. Fix, then rerun. While iterating on one failure, bun run ci <phase>
runs just that phase; bun run ci --list names them.
Do not stand in bun run build, bun run lint, bun run typecheck and
bun run test for it. lint and format fix in place, so they pass where CI
fails, and those four miss format:check, gen:readme --check,
check:scaffolds, every example, the tour, the docs suite and the coverage
model.
Report the result plainly, with the failing step's own output when there is one.
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.
- 5d ago First seen · 22 lines · 0 tokens per session scan A 0bf59f2d8c88
ci-check is a command published in the GitHub repository petarzarkov/dunx (21 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 268 tokens. 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
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
triage
Classify/label newly opened GitHub issues missing labels.
release
Release all packages at specified version.
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
hello
Say hello.