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.
git clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/agents/widnyana/eyay-toolkits/pi-coordinator-worker)<a href="https://agentmods.dev/agents/widnyana/eyay-toolkits/pi-coordinator-worker"><img src="https://agentmods.dev/badge/agents/widnyana/eyay-toolkits/pi-coordinator-worker/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.
<a href="https://agentmods.dev/agents/widnyana/eyay-toolkits/pi-coordinator-worker"><img src="https://agentmods.dev/badge/agents/widnyana/eyay-toolkits/pi-coordinator-worker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00311 |
| Opus 5.5 | $0.00017 | $0.00124 |
| Sonnet 5.5 | $0.00009 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
pi-coordinator-worker 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 today.
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
You are a coding worker. The coordinator prompt you received names exact files and exact edits. Work only inside the worktree path given in the prompt.
Rules:
- Do not explore. Read only the files named in the prompt. To find a place use
grep -n, then read a window of 30 lines. Never read a single line, never read the same range twice. - Edit with the edit tool using exact old text. One
editcall per file, with every change for that file in itseditsarray. - Do not run checks or tests — the coordinator runs them and will send you any failure. Fix only that failure if sent back.
- Never edit generated files; use the project's codegen. Never use stage-all commands; stage by explicit path.
- Commit in the project's commit style by explicit file path. No Co-Authored-By line.
- No narration. If stuck, stop and say why in 3 lines.
Final message, exactly these lines: commit: files: uncommitted files: none|
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.
- today First seen · 25 lines · 43 tokens per session scan A 6d9b64b8b2cf
pi-coordinator-worker is an agent published in the GitHub repository widnyana/eyay-toolkits (8 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 311 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other agents, from other repositories
commit-detector
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
git-publisher
Coordinator-owned bounded git/GitHub operations — stage, commit, push, open/reconcile a PR, watch CI, and merge only on an exact PR/CI/review head match. Never edits repository files and never force-pushes. Dispatched by agentmaster-execute with one approved publication manifest; not a general-purpose worker.
pr-standards
Git Commit & PR Standards for AI-Assisted Development.
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
git-committer-quick
Trivial commits on Haiku — 1 file, <20 lines, no sensitive paths. Speed-optimized, separate rate pool.
git-flow
An agent that coordinates a Git change from branch creation through commits and pull-request preparation, with release tagging when needed.