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/abubakarsiddik31/skill-manager/agents-mdgit clone --depth 1 https://github.com/abubakarsiddik31/skill-managerWrote 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.
[](https://agentmods.dev/instructions/abubakarsiddik31/skill-manager/agents-md)<a href="https://agentmods.dev/instructions/abubakarsiddik31/skill-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/abubakarsiddik31/skill-manager/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01190 | $0.01190 |
| Opus 5 | $0.00595 | $0.00595 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
skill-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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — Skill Manager
Stack: Tauri v2 (Rust backend) + React + TypeScript frontend, built with Vite.
Structure
src/
api/ the invoke client over Rust commands (skills.ts,
projects.ts, collections.ts)
components/
layout/ app chrome (Sidebar, Topbar)
skills/ skill grid (SkillList, SkillCard, SortToggle)
browse/ the full-window collections browser (BrowseView)
modals/ the four dialogs (Editor, CreateSkill,
AddProject, Projects)
ui/ shared primitives (ModalShell, icons)
hooks/ data + mutations (useGlobalSkills, useProjects, useProjectSkills)
utils/ pure helpers + tests (filtering, sidebar lists, time, markdown,
collection search)
types/ shared frontend types split by domain, barrel at types/index.ts
src-tauri/src/
commands/ tauri commands split by domain — skills.rs, create_skill.rs,
projects.rs, collections.rs; mod.rs holds the shared
managed-path validation (see the security note below)
collections/ GitHub collections: github.rs (HTTP + parsing), catalog.rs
(tree → skills), manifest.rs (public catalog +
bundled fallback), index.rs + skills.json (bundled
skill index — browsing built-ins costs no GitHub API
calls; regenerate the index when seed repos change),
install.rs (codeload tarball download into managed
roots + provenance — installs spend no GitHub API
quota), store.rs (user collections, cache)
skills/ one adapter per skills folder (claude, agents, copilot, ...),
plus tools.rs — the tool→folder registry driving the sidebar
projects.rs persisted list of tracked project folders
detect.rs project-folder discovery for the add-project picker
docs/ the landing page (GitHub Pages, docs/index.html)
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.
- 6d ago First seen · 106 lines · 1,190 tokens per session scan A ca0180e7cd8f
skill-manager AGENTS.md is an instructions file published in the GitHub repository abubakarsiddik31/skill-manager (23 stars, last pushed 6d ago), licensed MIT. It adds 1,190 tokens to every session, about $0.0060 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 2026-08-30.
Other instructions, from other repositories
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
moonproxy-desktop AGENTS.md
AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
CodePilot CLAUDE.md
Claude Code instructions for op7418/CodePilot, covering claude.md, 协作模式（作者 / claude code / codex）, 开发规则, 语义验收与反假数据 and 自检命令.
silent-Tiangong CLAUDE.md
Claude Code instructions for silent-rs/silent-Tiangong, covering claude.md, 项目概述, 常用开发命令, 构建 and 检查（快速验证）.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.
markra AGENTS.md
AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.