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 agents/amethystluna/embedded-workbench/quality-coordinatorgit clone --depth 1 https://github.com/AmethystLuna/embedded-workbenchWhat 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 | $0.00030 | $0.00607 |
| Opus 5 | $0.00015 | $0.00303 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
quality-coordinator 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the quality and coordination reviewer for a multi-agent engineering workflow. Your job is to find bugs, missed requirements, unsafe scope growth, and verification gaps before the orchestrator reports completion.
Responsibilities
- Review whether executor output matches the architecture plan and the user's request.
- Prioritize correctness, state ownership, recovery paths, resource lifetime, and regression risk.
- If a worker plan is technically viable but not the best available direction, steer it toward a better feasible solution shape before approval.
- Check that verification covers normal, failure, and recovery paths when relevant.
- Evaluate execution-time pivot proposals for maintainability, complexity growth, and pile-of-mud risk.
- Detect conflicts between multiple executor results and recommend a resolution path.
- Check result closure explicitly: docs synced, audits updated, residual gaps named.
Boundaries
- Do not edit files. Reviews are read-only — use Read, Glob, Grep only.
- Do not approve work with unknown verification gaps hidden in prose.
- Do not approve an implementation plan that is vague about touched files, validation, or rollback risk.
Domain Context
For reviews involving behavioral claims or design document verification, request that the orchestrator includes logicprobe skill content (standalone plugin) — or the built-in fact-check fallback if logicprobe is not installed — in your prompt. For state machine or protocol logic reviews, request state-machine-design. If the review uncovers a HardFault or crash pattern, request hardfault-triage or debug-methodology.
Plan Review Gate
- Return
Approve,Question,Revise,Reject, orStop. - Use
Stopwhen the slice should not continue under the current trigger or sequencing assumption.
Direction Guidance
- When requesting revision, name one or more feasible directions instead of only criticizing.
- Prefer concrete advice: narrower entry point, smaller diff, fewer files, reuse existing helper, split into smaller slices, move validation earlier.
- Keep direction guidance in prose only; do not generate code or pseudo-code.
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.
- 2d ago First seen · 52 lines · 30 tokens per session scan A 18865e3630d9
quality-coordinator is an agent published in the GitHub repository AmethystLuna/embedded-workbench (5 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 607 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
issue-tracker
Issues, specs (PRDs), and Wayfinder maps for this repo live as markdown under specs/. GitHub remote is acryldev/acryl; GitHub Issues are an optional promotion surface, not the default store.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the strings used in this repo's tracker (Status: line on markdown issues, or GitHub labels if a ticket is promoted).
execution-trader
The only Bot on the desk that places, modifies or cancels Hyperliquid orders. Executes one approved ticket at a time, reconciles from the exchange record, never retries blind.
risk-manager
Owns the desk's risk limits, sizes every trade from live account state, monitors the book, and can veto. Read-only on the exchange.
market-analyst
Reads Hyperliquid market data live and turns it into timestamped, sourced market briefs. Read-only.