What is forge-skills CLAUDE.md?

Repository instructions for Forge Skills, a set of written procedures that guide coding agents from an issue, ticket, or pull request to a completed fix. They also describe Blacksmith Orchestrate, which coordinates several such tasks.

Following the repository's workflow, running its shell-based tests, and safely editing the Forge and Blacksmith skill instructions.

They tell agents how the repository works, how to install the skills, and how to test changes to the instruction text. This matters because changing the prose changes agent behavior.

How radimsem/forge-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to radimsem/forge-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/radimsem/forge-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/radimsem/forge-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/radimsem/forge-skills/claude-md.svg)](https://agentmods.dev/instructions/radimsem/forge-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/radimsem/forge-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/radimsem/forge-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,885 This file is loaded in full into every session.

When invoked 1,885 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.

Model	Per session	Once invoked
Fable 5.1	$0.01885	$0.01885
Opus 5	$0.00942	$0.00942
Sonnet 5	$0.00377	$0.00377
Haiku 4.5	$0.00188	$0.00188

Measured 6d ago against content hash 6eafb023b93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

forge-skills CLAUDE.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.

CLAUDE.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

This repo ships two skills, not an application. The primary deliverable is forge — an agent-runtime-agnostic skill that turns an issue/ticket/PR reference into a shipped fix through a gated 12-step workflow. Alongside it, blacksmith-orchestrate is forge's orchestration wrapper: it takes several issues, a milestone, or a written plan, decides which of them collide and which can run in parallel, then dispatches one ordinary forge run per task. "The code" is the prose in each skill's markdown; the only executable is the installer.

Because the artifact is instructions an agent reads and follows, edits to skills/** are changes to behavior. Treat wording with the same care as code: a sentence in SKILL.md is a contract the running agent will obey literally.

Commands

Everything lives in POSIX sh; there is no package manager, build step, or linter config.

sh tests/install_test.sh          # run the installer unit suite
sh tests/docs_test.sh             # run the structural-invariants suite across both skills' prose
sh tests/install_test.sh | grep FAIL   # quick check for failures; exits non-zero if FAILS>0
sh install.sh -h                  # see installer usage

tests/install_test.sh sources install.sh with INSTALL_SH_SOURCED=1, which is the guard that prevents main() from running on source (see the bottom of install.sh). This lets the suite unit-test individual functions (parse_args, build_skill_group_cmd, run_installs, …) by stubbing npx/claude.
tests/docs_test.sh asserts structural invariants across the shipped prose for both skills: relative markdown links resolve, the flag tables agree across SKILL.md/references/flags.md/README.md, no TBD/TODO/FIXME placeholders remain, and every references/modes/*.md (forge) or references/*.md (blacksmith-orchestrate) file carries a manual verification recipe.
There is no single-test selector; each suite is one script. To isolate a check, comment out the others or add a temporary assert_* near the function under test.
shellcheck is not configured or installed here, but the scripts are written to pass it — keep new shell POSIX-clean (no bashisms).

Read the full file on GitHub · 97 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.

6d ago First seen · 97 lines · 1,885 tokens per session scan A 6eafb023b93d

Subscribe to this mod's changes

forge-skills CLAUDE.md is an instructions file published in the GitHub repository radimsem/forge-skills (15 stars, last pushed 13d ago), licensed MIT. It adds 1,885 tokens to every session, about $0.0094 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.

agent-skills

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

forge-skills: Instructions file for Claude Code