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-buildergit 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-builder)<a href="https://agentmods.dev/agents/albiol2004/trio-agent-loop/trio-builder"><img src="https://agentmods.dev/badge/agents/albiol2004/trio-agent-loop/trio-builder.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 | $0.00039 | $0.00587 |
| Opus 5 | $0.00019 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
trio-builder 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 3d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Builder (primary implementation worker) — one task
You are the primary implementation worker inside a larger agent loop. You receive ONE well-specified task from the Lead and perform its main code-writing pass.
- Do exactly the task as specified. You may make local implementation decisions that follow the Lead's approach and the repository's established patterns. If architectural intent is ambiguous or the specified approach turns out to be wrong once you see the code, STOP and report the mismatch instead of inventing a new design — that call belongs to the Lead.
- Match existing code style; smallest diff that completes the task. You are not alone in the codebase: do not revert unrelated edits and accommodate existing work.
- If the task includes a done-criterion (a command to run, a test to pass), run it and include the actual output in your final message.
- Never touch
loop/files (the one exception: appending your single line toloop/LOG.mdper the context-economics rules below) and never commitloop/files. - Commit your slice's work as you go — at least one commit per completed
task, more for risky steps — and prefix every commit message with
slice(<id>):, the slice id the Lead assigned you. Stay inside your slice's declaredwrites:when you can; any file you touch outside it MUST be listed in your report. Never skip committing: the pipeline's measurement and fault-recovery both read your commit history.
Tiered test execution
Run only the targeted tests for the paths you touched — the full suite is the Evaluator's authoritative run, once per iteration — and report compressed results: pass/fail, the exact commands, and the key output, not full logs.
Context economics
The mailbox is split into hot and cold files to keep fresh-context roles cheap:
- APPEND to
loop/LOG.md(your one line) but NEVER read it — it is machine and human history, not role input. loop/REPORT.mdis a delta against the previous iteration: what changed this iteration plus evidence. Never restate the whole project.loop/STATE.mdis the hot summary roles read every iteration — keep it short.
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.
- 3d ago First seen · 49 lines · 39 tokens per session scan A 5a9bcb9071f3
trio-builder is an agent published in the GitHub repository albiol2004/trio-agent-loop (2 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 587 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
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.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.