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 instructions/danielgap/openclaw-planitor/agents-mdgit clone --depth 1 https://github.com/danielgap/openclaw-planitorWhat 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 | $0.00593 | $0.00593 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
openclaw-planitor AGENTS.md 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.
What it actually says
AGENTS.md – Planitor
Reglas de Delegación
Planitor NO ejecuta tareas directamente (salvo <5s). Todo → sessions_spawn.
Pipeline
- Leer
.agents/skills/pipeline-orchestrator/SKILL.md - Cada fase → sessions_spawn con prompt específico
- Validar output antes de pasar a siguiente fase
- Si falla 2 veces → escalar a el usuario
Restricciones por Subagente
- Una acción por subagente (como Escapeitor)
- Prompt ≤500 palabras por subagente
- No pedir que lea más de 5 archivos por subagente
- Si la tarea necesita más contexto → ponerlo en un archivo y decirle "lee X.md y aplica"
Delegación por Tipo
| Tarea | Agente | Modelo |
|---|---|---|
| Scraping/extracción web | Extractor | glm-4.7-flash |
| Búsquedas (Tavily, etc.) | Extractor | glm-4.7-flash |
| Google Trends | Scout | glm-5 |
| Análisis e investigación | Scout | glm-5 |
| Redacción documento final | Escritor | glm-5.1 |
| Fases creativas del pipeline | Scout/Escritor | glm-5.1 |
| Fases mecánicas del pipeline | Scout | glm-5-turbo |
| STRATEGY dual (Juez A) | Razonator | glm-5.1 |
| STRATEGY dual (Juez B) | Visionator | gpt-5.5 |
| BUILD dual (Juez A) | Razonator | glm-5.1 |
| BUILD dual (Juez B) | Visionator | gpt-5.5 |
| JUDGE dual (Juez A) | Razonator | glm-5.1 |
| JUDGE dual (Juez B) | Visionator | gpt-5.5 |
Kanban
- ANTES:
POST /api/kanban/agent/tasks→ crear tarea - DELEGAR:
sessions_spawncon taskId - DESPUÉS:
PATCH /tasks/{taskId}con status=done + resultado
Ver skill kanban-tasks para API.
Project Paths
Al delegar trabajo, SIEMPRE incluir ruta projects/<proyecto>/. Agentes trabajan en projects/<proyecto>/, nunca en su directorio.
Fallback
- Primario → 2. Secundario → 3. code → 4. Escalar a el usuario
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 · 48 lines · 593 tokens per session scan A d795fa42cf49
openclaw-planitor AGENTS.md is an instructions file published in the GitHub repository danielgap/openclaw-planitor (5 stars, last pushed 4mo ago), licensed MIT. It adds 593 tokens to every session, about $0.0030 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 instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
browser-agent CLAUDE.md
Instructions for uiuing/browser-agent, a project described as: An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
statbotics-mcp-server CLAUDE.md
Claude Code instructions for withinfocus/statbotics-mcp-server, covering claude instructions for statbotics mcp server, project overview, project structure, source code architecture and test architecture.