personal-mcp AGENTS.md

personal-mcp AGENTS.md is an instructions file for Codex, OpenCode from jaimeehd/personal-mcp. It costs 11,617 tokens per session, scanned A, original, MIT.

A set of project instructions for working on a personal MCP server, including its configuration, journal, modules, and safety rules. MCP is a way for an agent to use tools supplied by another service.

In plain words
What is it for?
Use it when maintaining that personal-mcp project, especially when editing configuration, synchronizing settings, or preparing repository changes.
Why use it?
It helps an agent avoid changing the wrong configuration file and prevents sensitive or identifying material from being published in a public repository.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/jaimeehd/personal-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/jaimeehd/personal-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for personal-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jaimeehd/personal-mcp/agents-md.svg)](https://agentmods.dev/instructions/jaimeehd/personal-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jaimeehd/personal-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jaimeehd/personal-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,617 This file is loaded in full into every session.
When invoked 11,617 The same file — it is already loaded in full.
Security scan A 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.11617 $0.11617
Opus 5 $0.05809 $0.05809
Sonnet 5 $0.02323 $0.02323
Haiku 4.5 $0.01162 $0.01162

Measured 4d ago against content hash ec102988d5f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

personal-mcp AGENTS.md scanned grade A with 2 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- ✅ **Escaneo AST pre-ejecución de scripts Python (v1.4.32)**: `validate_shell_execution()` analiza el árbol sintáctico (AST) con `script_analyzer.py` en scripts `.py` para detectar importaciones de red (`requests`, `soc

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `src/shell_resolver.py` — dataclass `ShellInfo`, `SHELL_REGISTRY` (4 shells), `resolve_shell()`, `_find_executable()`, `_find_git_bash()`. `_find_git_bash()` ejecuta un `subprocess.run(timeout=5)` **síncrono** — cualqu
AGENTS.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

personal-mcp — AGENTS.md

⚠️ LEE ESTO PRIMERO SI VAS A TOCAR config.json: El config.json en la raíz de este repo es solo un espejo de solo lectura. NO lo edites pensando que cambia algo — no lo hace. El único config real que carga el servidor está en ~/.personal-mcp/config.json (ver AppConfig.default_path() en src/config.py). Para actualizar el espejo tras editar el oficial, ejecuta sync-config.ps1 desde la raíz del repo. Explicación completa en CONFIG-GUIA.md.

⚠️ SANITIZAR ANTES DE ACTUALIZAR EL REPO — OBLIGATORIO (regla del dueño, 2026-08-13):

  • El repo es público en GitHub. Todo git push publica contenido permanente que cualquiera puede ver.
  • Antes de CADA git add + git commit + git push, correr el sweep de sanitización y exigir cero coincidencias fuera de AGENTS.md (este bloque contiene la regla misma y los tokens): git grep -nE "C:\\\\Users\\\\User|C:\\\\Repos|HikBioAccess|BookStore|VisorCamara|atril|doc-pipeline|lauris|ingesoft|Bitacora|ant\\.dir\\.ant" -- . ':!AGENTS.md'
  • Si el sweep encuentra algo, reemplazar con los placeholders estándar (usuario, C:\Users\usuario\Repos, MiProyecto — en CONFIG-GUIA.md: C:\Users\TuUsuario\Repos) antes de commitear, nunca después. Un commit ya pusheado queda para siempre en el historial remoto.
  • Incidente real 2026-08-13: la raíz de repos local y la carpeta .ssh del usuario llegaron al remoto público vía CHANGELOG.md y AGENTS.md. Corregido doble: hacia adelante (placeholders en docs) y hacia atrás (historial reescrito como único commit raíz sanitizado 2dc4817, force-push; los 6 commits anteriores salieron de main). La reescritura fue aprobada explícitamente por el dueño. Lección: correr el sweep ANTES de cada push, no solo antes de cada commit — el primer git push de la corrección casi repite la fuga en el historial.

⚠️ HISTORIAL GIT — CRÍTICO, NO TOCAR:

  • main es el historial público del repo (1 commit raíz, sanitizado). Todo trabajo nuevo va en main.
  • La rama local historico contiene los 65 commits previos del proyecto, con datos personales y de configuración real. Es solo local y nunca debe pushearse.
  • NUNCA ejecutar git gc --prune=now ni git prune en este repo, ni borrar la rama historico, ni los tags locales v1.4.14/v1.4.33 (ni feat/linux-support, también local-only) — todo eso destruiría el historial completo que se conserva a propósito en esta máquina.
  • Para cualquier experimento de reescritura de historial, trabajar sobre una copia (git branch respaldo historico), nunca contra historico misma.

Read the full file on GitHub · 260 lines

Changes

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.

  1. 4d ago First seen · 260 lines · 11,617 tokens per session scan A ec102988d5f1

Subscribe to this mod's changes

personal-mcp AGENTS.md is an instructions file published in the GitHub repository jaimeehd/personal-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 11,617 tokens to every session, about $0.0581 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens