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/pavelzw/skill-forge/agents-mdgit clone --depth 1 https://github.com/pavelzw/skill-forgeWrote 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/pavelzw/skill-forge/agents-md)<a href="https://agentmods.dev/instructions/pavelzw/skill-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/pavelzw/skill-forge/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 | $0.00613 | $0.00613 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
skill-forge 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 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.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Summary
This repository contains conda packages for coding agent skills.
Structure
"Skills" are text files that AI-based coding agents can read to enhance their understanding of a complex topic or tool, like an internal library or company-specific guidelines and knowledge. They're usually structured as markdown files with brief documentation, instructions, code examples, and usage guidelines. A skill may reference additional markdown files in a references/ subdirectory that are read on demand.
Every skill is shipped in a conda package located in share/agent-skills/<skill>/SKILL.md (plus additional files).
Mirroring from skills.sh
When mirroring a skill from https://skills.sh/, start with the example in examples/mirror-skills.sh. You then need to look into the repository and find the actual skill directory.
Update Strategies for Mirrors
If you build a skill that fetches data from a remote source, please also add it to .github/workflows/autobump.yml with appropriate update strategies.
- github-latest-release: Use this strategy if the repository has releases and the latest release is somewhat recent.
- git-main: Use this strategy otherwise.
Updating skill contents
When the user asks you to update the content of a skill, follow these steps:
- Check out the latest version of the tool or API that the skill is based on to a temporary location.
- Investigate which parts of the skill still accurately reflect the current state of the tool or API and which parts need to be updated or added to the skill.
- Apply the minimal viable update to the skill's content. This means: a) NEVER change information in the skill that is still accurate, exhaustive, correct, and up-to-date. b) ONLY change information that is outdated, incorrect, or missing. c) Often times, this means edits will be local to a subsection or a few paragraphs, or new subsections will be added.
- If there is a
PROMPT.mdnext to therecipe.yaml, read that file and also include it in how you update the skill.
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.
- 4d ago First seen · 55 lines · 613 tokens per session scan A 4ccf15f1cbb5
skill-forge AGENTS.md is an instructions file published in the GitHub repository pavelzw/skill-forge (23 stars, last pushed today), licensed BSD-3-Clause. It adds 613 tokens to every session, about $0.0031 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
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.