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 skills/leefowlercu/agent-kit/subsystem-mdnpx skills add leefowlercu/agent-kit --skill subsystem-mdgit clone --depth 1 https://github.com/leefowlercu/agent-kitWhat 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 | $0.00010 | $0.02158 |
| Opus 5 | $0.00005 | $0.01079 |
| Sonnet 5 | $0.00002 | $0.00432 |
| Haiku 4.5 | $0.00001 | $0.00216 |
Grade A, and why
subsystem-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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expected Input
Use the subsystem name supplied by the user as <subsystem-name>.
The subsystem documentation file is located at docs/subsystems/<subsystem-name>/README.md.
Check if this file exists:
- If it does not exist: Proceed to Initialization Mode
- If it exists: Proceed to Reconciliation Mode
Shared Guidelines
When drafting or updating this documentation, you
- MUST focus on the high-level aspects of the requested subsystem, ensuring that it provides clear insights into its functionality, design principles, and interactions with other parts of the system.
- MUST NOT include low-level implementation details, code snippets, or exhaustive technical specifications, as those may change frequently during development.
- MUST ensure that the documentation is accurate and reflects the current state of the requested subsystem as understood from your analysis of the codebase.
- MUST strike a balance between being comprehensive and concise, providing enough information to be useful without overwhelming the reader with unnecessary details.
Section Description Syntax: **<section-identifier>: <section-level>** { - section-title} - <section-description> { - section-example} {, section-example}...
Section Description Examples:
**Subsystem Title: H1** - The name of the subsystem in Title Case.**Subsystem Tagline: N/A** - A brief, catchy tagline that summarizes the subsystem's purpose or mission.**Documented Version: N/A** - The current documented version of the subsystem. - **Documented Version**: v0.1.0, **Documented Version**: N/A**Design Principles: H2** - Design Principles - An explanation of the core design principles and architectural patterns.
The structure of the subsystem README.md file MUST include ONLY the following sections, in order:
- Subsystem Title: H1 - The name of the subsystem in Title Case. Derive a suitable title based on the subsystem's purpose and functionality.
- Subsystem Tagline: N/A - A brief, catchy tagline that summarizes the subsystem's purpose or mission.
- Documented Version: N/A - The version of the requested subsystem being documented, derived from git tags or version files. If no versioning is found use "N/A". -
**Documented Version**: v0.13.0, **Documented Version**: N/A - Last Updated: N/A - The date when the documentation was last updated. Use the format YYYY-MM-DD. -
**Last Updated**: 2024-06-15 - ToC: H2 - Table of Contents - A markdown table of contents that links to the subsequent header sections in the README.md.
- Overview: H2 - Overview - A brief, high-level description of the requested subsystem, its purpose, goals, and key features.
- Design Principles: H2 - Design Principles - An explanation of the core design principles and architectural patterns that guide the development of the requested subsystem.
- Key Components: H2 - Key Components - A high-level description of the main components or modules that make up the requested subsystem.
- Integration Points: H2 - Integration Points - An outline of how the requested subsystem integrates with other subsystems or components within the codebase.
- Glossary: H2 - Glossary - Definitions of any specialized terms or concepts relevant to the requested subsystem.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 164 lines · 10 tokens per session scan A 6bc403d0c13e
subsystem-md is a skill published in the GitHub repository leefowlercu/agent-kit (6 stars, last pushed 29d ago), licensed MIT. It adds 10 tokens to every session and 2,158 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…