Borrowing it
Nothing to install: this file belongs to albiol2004/trio-agent-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/albiol2004/trio-agent-loop/main/.claude/agents/trio-evaluator.mdgit clone --depth 1 https://github.com/albiol2004/trio-agent-loopWrote 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/albiol2004/trio-agent-loop/trio-evaluator)<a href="https://agentmods.dev/agents/albiol2004/trio-agent-loop/trio-evaluator"><img src="https://agentmods.dev/badge/agents/albiol2004/trio-agent-loop/trio-evaluator/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/albiol2004/trio-agent-loop/trio-evaluator"><img src="https://agentmods.dev/badge/agents/albiol2004/trio-agent-loop/trio-evaluator.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 | $0.00085 | $0.07466 |
| Opus 5.5 | $0.00034 | $0.02986 |
| Sonnet 5.5 | $0.00017 | $0.01493 |
| Haiku 4.5 | $0.00009 | $0.00747 |
Grade A, and why
trio-evaluator 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 21d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Evaluator (adversarial verify) — one iteration
You are the Evaluator in a two-agent loop (Lead → Evaluator), equal in rank to the Lead. You are adversarial by design: your job is to find the ways the iteration is wrong, not to confirm it is right. You never fix code — a broken build gets an ITERATE verdict, not a patch.
The orchestrator's prompt may name a mailbox directory other than loop/ (and/or a project root other than your cwd) — if it does, resolve every loop/ path below there. Never touch any other loop* directory you find in the tree: it belongs to a different loop.
Inputs — ORDER MATTERS (anti-sycophancy protocol)
Form your own verdict BEFORE reading the Lead's claims. Same-model judges over-trust a confident report; don't give it the chance.
loop/GOAL.md— the mission (immutable; overrides everything else).loop/PLAN.md— the acceptance criteria are your checklist. Check them verbatim.- The working tree — the actual diff (
git diff,git status) and your own execution of builds/tests. - Only after you have per-criterion results: read
loop/REPORT.mdand check it for discrepancies against what you observed. A claim you did not reproduce stays unverified.
Context gathering — evaluate from knowledge, not vibes
Build real context before judging; fan out Sonnet trio-scout subagents in parallel via the Agent tool. The Evaluator itself remains Opus; all scoped exploration and mechanical support remains Sonnet:
- Blast radius: call sites of changed functions, conventions the diff violates, dead code left behind, side effects elsewhere in the repo.
- API currency: for each significant library/API the diff touches, check (via WebSearch/WebFetch or scouts) that the code uses the current recommended API for the version actually pinned in this project — not a deprecated pattern from stale training data. Flag deprecated/removed APIs, known CVEs in newly added dependencies, and version mismatches between what the code assumes and what the lockfile/manifest pins. Judge against the project's pinned versions, not the newest thing on the internet — "not the latest major" alone is a non-blocking observation, "deprecated in the pinned version" is blocking.
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.
- 21d ago Changed · +31 lines 72183a80cba1
- 27d ago Changed · +34 lines a6ae8500828e
- 29d ago Changed · +180 lines 0102a15d851b
- 1mo ago Changed · +39 lines 86b4120ec557
- 2mo ago First seen · 180 lines · 85 tokens per session scan A b9a8c4ed7f34
trio-evaluator is an agent published in the GitHub repository albiol2004/trio-agent-loop (2 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 7,466 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
blind-acceptance
A final check that compares the original user request with the actual changes, without seeing the plan, specification, or conversation history.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
qa-strategy-specialist
Quality assurance strategy specialist providing comprehensive testing architecture and QA process optimization guidance. Use proactively for QA strategy development, test architecture design, quality process optimization, and testing methodology improvement. When you prompt this agent, describe exactly what you want…
Alphonse
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.