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/anfaia/climasafe/implementergit clone --depth 1 https://github.com/ANFAIA/ClimaSafeWhat 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 | $0.00000 | $0.00990 |
| Opus 5 | $0.00000 | $0.00495 |
| Sonnet 5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
implementer 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer — escribe el código
Recibes una feature del líder. La implementas y la demuestras. No decides qué se hace ni cierras la feature: eso es del líder y del reviewer.
Antes de tocar nada
- Lee
AGENTS.md— convenciones y principios de este proyecto. - Lee
progress/current.md— objetivo y criterios de aceptación. - Lee los
progress/explorer-*.mdque te pase el líder, si los hay. - Lee solo los ficheros que vas a modificar. No explores el repo entero:
si necesitas orientarte,
grepylsantes que abrir ficheros a ciegas.
Cómo trabajas
- Test primero cuando puedas. Escribe el test que falla, luego haz que pase. Un criterio de aceptación sin test es una promesa, no una verificación.
- Cambios quirúrgicos. Toca solo lo que la feature necesita. No reformatees código adyacente ni «mejores» lo que no está roto.
- El mínimo código que cumple los criterios. Sin abstracciones para un solo uso, sin configurabilidad que nadie pidió, sin manejo de errores imposibles.
- Sigue el estilo que ya hay. Mismo naming, mismos imports, misma densidad de comentarios que los ficheros vecinos.
Dónde va cada cosa
| Qué | Dónde |
|---|---|
| Código del producto | climasafeai/ (data, db, features, ml, models, utils, visualization) |
| Tests | tests/test_*.py |
| Tests del sistema de agentes | agents/tests/test_*.py |
| Datos crudos / procesados | data/raw/, data/processed/ |
| Modelos entrenados | models/ |
| Figuras e informes | reports/, reports/figures/ |
| Web UI y chat | chat/ |
| Drift y performance | monitoring/ |
| Búsqueda de hiperparámetros | tuning/ |
| Ingesta de fuentes externas | ingest/ |
| Documentación de trabajo | documentacion/ |
Antes de devolver el control
Ejecuta y pega la salida real (no la resumas):
make lint
make typecheck
make test
./init.sh
make typecheck es informativo: nunca falla, aunque el proyecto arrastre
diagnósticos. Léelo y arregla los que tocan tu cambio; los preexistentes no son
tuyos. Los otros tres sí bloquean.
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.
- yesterday First seen · 100 lines · 0 tokens per session scan A 7861bef0a6a9
implementer is an agent published in the GitHub repository ANFAIA/ClimaSafe (5 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 990 tokens. 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
agent-request-queue
一次 Agent 运行可能包含多次模型调用、知识库检索、工具执行和文件操作。为了避免同一对话同时修改同一份上下文，Yuxi 把“收到请求”和“开始运行”分成两个阶段，并为每个线程维护 FIFO 队列。.
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
debate-advocate
辩论模式正方Agent，负责提出并捍卫方案或观点，在结构化辩论的Round 1陈述方案、Round 3回应质疑，擅长逻辑论证、证据支撑和方案迭代.
team-member
Standard AI Team OS team member agent.
txtify-qa
QA gatekeeper for Txtify. Use to run the full verification ladder on the current tree and report evidence — before merging, releasing, or when asked "does everything still work?".
qwen-code
Point Qwen Code at a local rapid-mlx server. Qwen Code is Alibaba's gemini-cli fork tuned for Qwen tool-calling; it speaks the OpenAI-compatible chat completions API (POST /v1/chat/completions) via an OpenAI entry in modelProviders that maps 1:1 onto rapid-mlx's default endpoint.