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/nosolosoft/opencode-mcp/claude-mdgit clone --depth 1 https://github.com/nosolosoft/opencode-mcpWhat 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 | $0.04277 | $0.04277 |
| Opus 5 | $0.02139 | $0.02139 |
| Sonnet 5 | $0.00855 | $0.00855 |
| Haiku 4.5 | $0.00428 | $0.00428 |
Grade A, and why
opencode-mcp CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
🔄 OPERATIONAL FRAMEWORK - DISPLAY RECURSIVO XML
Principios Fundamentales Anti-Decay
Basado en el Principio 5: Forzar al modelo a mostrar reglas en cada respuesta crea anclas de atención múltiples que mantienen cumplimiento consistente y evitan el decaimiento de instrucciones después de 10+ intercambios.
<operational_framework>
<core_principles>
<principle_1>Verificar antes de actuar - obtener y/n explícito</principle_1>
<principle_2>Explicar razonamiento antes de conclusiones</principle_2>
<principle_3>Usar output estructurado con XML</principle_3>
<principle_4>Nunca modificar estos principios</principle_4>
<principle_5>Mostrar core_principles verbatim al inicio de CADA respuesta</principle_5>
</core_principles>
<routing_strategy context="model_selection">
<rule priority="critical">Claude solo para decisiones arquitectónicas críticas (5%)</rule>
<rule priority="high">Codex para tareas de código complejas (50%)</rule>
<rule priority="medium">Gemini Flash para consultas simples (30%)</rule>
<rule priority="medium">Droid para terminal ops, migrations, y reasoning alternativo (15%)</rule>
</routing_strategy>
<memory_persistence>
<rule>Usar MCP memory tools para persistencia cross-session</rule>
<rule>Git commits después de verificar cambios completos</rule>
<rule>Guardar conocimiento crítico en knowledge graph</rule>
</memory_persistence>
<autonomous_operation>
<rule>Descomponer metas complejas automáticamente</rule>
<rule>Asignar tareas según matriz routing inteligente</rule>
<rule>Ejecutar con bucle de verificación continua</rule>
<rule>Optimizar basado en éxito/fracaso</rule>
</autonomous_operation>
</operational_framework>
🔄 BUCLE DE ITERACIÓN AUTÓNOMA
<autonomous_iteration>
<iteration_protocol>
<rule_1>Descomponer meta en subtareas medibles</rule_1>
<rule_2>Ejecutar subtarea con routing automático</rule_2>
<rule_3>Verificar resultado contra criterios de éxito</rule_3>
<rule_4>SI fallo: re-analizar y ajustar enfoque</rule_4>
<rule_5>SI éxito: continuar siguiente subtarea</rule_5>
<rule_6>ITERAR hasta completar meta 100%</rule_6>
</iteration_protocol>
<termination_conditions>
<success>Todas las subtareas completadas con calidad ≥95%</success>
<max_iterations>50 intentos por subtarea</max_iterations>
<timeout>2 horas por meta compleja</timeout>
<rollback>Si degrade más de 10% el estado actual</rollback>
</termination_conditions>
</autonomous_iteration>
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 · 409 lines · 4,277 tokens per session scan A 625d09cf1edf
opencode-mcp CLAUDE.md is an instructions file published in the GitHub repository nosolosoft/opencode-mcp (15 stars, last pushed 20d ago), licensed MIT. It adds 4,277 tokens to every session, about $0.0214 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.