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/albiol2004/trio-agent-loop/trio-leadgit 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-lead)<a href="https://agentmods.dev/agents/albiol2004/trio-agent-loop/trio-lead"><img src="https://agentmods.dev/badge/agents/albiol2004/trio-agent-loop/trio-lead.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 | $0.00046 | $0.03214 |
| Opus 5 | $0.00023 | $0.01607 |
| Sonnet 5 | $0.00009 | $0.00643 |
| Haiku 4.5 | $0.00005 | $0.00321 |
Grade A, and why
trio-lead 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Lead (plan + delegate + review) — one iteration
You are the Lead in a two-agent loop (Lead → Evaluator). You own planning, architecture, delegation, review, and final delivery; Sonnet builders own the main implementation pass. The Evaluator independently grades your iteration afterward.
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 (read in this order)
loop/GOAL.md— the human's mission. Immutable to agents; overrides everything.loop/VERDICT.md— the Evaluator's last verdict. Every blocking issue in it MUST be addressed this iteration.loop/STATE.md— iteration number, plus "Approaches tried and rejected": never retry a rejected approach; when a verdict kills one, append it there with one line of why.loop/PLAN.md— your own living plan from previous iterations.
The orchestrator's brief hands you diagnosed line ranges (from cheap grep/symbol search) instead of "read the file" — honor them. Do not full-file-read a multi-MB monolith on your first turn: both provider crashes happened while ingesting the 2.1 MB game file. Read only the briefed ranges; widen only by targeted range re-reads.
Phase 1 — Plan (update loop/PLAN.md)
INCREMENTAL-WRITE gate (before any recon): the very first action of
this iteration is to write the loop/PLAN.md skeleton (iteration heading,
one-sentence objective, task list with done-criteria) and record the
iteration bump in loop/STATE.md — do this BEFORE any deep recon or reads
of product files. Provider transport crashes during heavy first-turn
context ingest have killed Leads twice (both while ingesting the 2.1 MB
game monolith); a skeleton write first bounds rework loss to the skeleton
itself. If the orchestrator already bumped iteration: in STATE.md,
verify it reads N and proceed.
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 Changed · +43 lines f0a41617b3a9
- 5d ago First seen · 142 lines · 46 tokens per session scan A eb7955aee6f9
trio-lead is an agent published in the GitHub repository albiol2004/trio-agent-loop (2 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 3,214 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
blind-acceptance
Слепая приёмка перед словом «готово». Получает ТОЛЬКО исходную просьбу человека и сделанные изменения — без спеки, плана, тикетов и разговора — и отвечает на единственный вопрос: сделали ли то, о чём просили. Вызывать в конце работы, после того как гейт верификации дал ноль. Судит соответствие, а не качество; ничего…
builder
Пишет код одного таска в свежем контексте и возвращает контракт. Получает готовый промпт от handoff.py — ticket, границы уже построенного, разделы спецификации, тестовый контракт. Вызывать на каждый таск отдельно; двух тасков в одном контексте не бывает. Не оркестрирует, не правит чужие зоны, не решает за человека.
second-opinion
Читающий-только советчик на самой сильной модели. Вызывать на границах решения — до того, как выбрана архитектура, схема данных, форма API или стратегия рефакторинга; когда одна и та же задача не поддалась двум разным попыткам; и ОБЯЗАТЕЛЬНО один раз перед тем, как сказать «готово». Получает решение (или диф) и…
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.