agentmods.dev

skills-manager AGENTS.md

Repository-specific instructions for Skills Manager, a macOS app that discovers, edits, imports, and deletes skill packages for several AI coding agents. They describe its Tauri desktop framework, React interface, commands, architecture, and frontend-to-backend connection.

In plain words
What is it for?
Use them when developing or releasing Skills Manager, especially when running the app, building its frontend or desktop package, or changing the filesystem and backend contract.
Why use it?
They give an agent the project rules and correct commands before it changes the code. This reduces mistakes caused by treating the app like an ordinary web project.

Instructions file for CodexOpenCode

5 1mo ago A scan 1,709 tokens original MIT
View the source file Enzoding/skills-manager
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/enzoding/skills-manager/agents-md
Clone the repo
git clone --depth 1 https://github.com/Enzoding/skills-manager

Made for: Codex, OpenCode.

Per session 1,709 This file is loaded in full into every session.
When invoked 1,709 The same file — it is already loaded in full.
Security scan A 0 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 $0.01709 $0.01709
Opus 5 $0.00855 $0.00855
Sonnet 5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured yesterday against content hash 1d7c351162fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills-manager 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 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.

AGENTS.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to WARP (warp.dev) when working with code in this repository.

Overview

Skills Manager is a macOS desktop app (Tauri 2 + React) that discovers, imports, edits, and deletes the SKILL.md-based skill packages used by ~12 AI coding agents (Claude Code, Cursor, Codex CLI, Copilot, etc.). All filesystem work happens against per-agent skills directories under the user's home (e.g. ~/.claude/skills/, ~/.codex/skills/).

Commands

package.json is the source of truth for scripts (the README's npm run tauri dev / npx tauri build also work via the Tauri CLI but differ in name):

  • npm install — install JS deps (Rust deps build automatically on first Tauri run).
  • npm run dev — run the full desktop app in dev mode (tauri dev; spawns Vite via beforeDevCommand).
  • npm run dev:client — Vite-only frontend on http://localhost:5173 (no Rust backend; invoke calls will fail).
  • npm run build — Vite build of the frontend into dist/ only. This is NOT the app build; it's the beforeBuildCommand Tauri runs.
  • npm run tauri:build — full release build, then strips the quarantine attribute (xattr -cr) so the .app opens locally. Output: src-tauri/target/release/bundle/{dmg,macos}/.

There is no test, lint, or formatter tooling configured (no ESLint/Prettier/Vitest, no Rust tests). Do not invent test commands; validate changes by building and running the app.

Release & Versioning

Release versions must stay synchronized across:

  1. package.json
  2. package-lock.json
  3. src-tauri/Cargo.toml
  4. src-tauri/tauri.conf.json

Use SemVer:

  • Patch (x.y.Z) for fixes only.
  • Minor (x.Y.0) for user-facing UI/behavior changes or new functionality.
  • Major (X.0.0) for breaking package/install/data compatibility changes.

Release checklist:

  1. Decide the next version from the changes since the latest GitHub release.
  2. Run npm version <version> --no-git-tag-version to update package.json and package-lock.json.
  3. Manually update src-tauri/Cargo.toml and src-tauri/tauri.conf.json to the same version.
  4. Add a dated section to CHANGE.md.
  5. Confirm Apple Developer ID signing and notarization are configured before publishing a public macOS release. A valid release must not be ad-hoc signed: security find-identity -v -p codesigning should show a Developer ID Application identity, codesign -dv --verbose=4 <app> should show a TeamIdentifier, and spctl -a -vvv -t open <dmg> should accept the DMG.
  6. Validate with npm run build and npm run tauri:build.
  7. Only after signing/notarization verification passes, commit the version/changelog changes, tag the same commit as v<version>, push the branch and tag, then create a GitHub release from that tag.

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 1,709 tokens per session scan A 1d7c351162fb

Subscribe to this mod's changes

skills-manager AGENTS.md is an instructions file published in the GitHub repository Enzoding/skills-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,709 tokens to every session, about $0.0085 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.

Backend and APIsFrontendGit and workflow
Related

Other instructions, from other repositories

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

buildNext

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

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.

vercel/next.js · 7,296 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

spec-kit 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 · 7,040 tokens

langchain 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 · 4,345 tokens