claude_skills: Instructions file for Claude Code

AGENTS.md

claude_skills AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Jamie-BitFlight/claude_skills. It costs 2,804 tokens per session, scanned A, original, MIT.

A repository guide that tells coding agents how to work in the Claude Skills project, including its structure, evidence standards, setup, and essential commands. An AGENTS.md file is a set of instructions stored with a codebase.

In plain words
What is it for?
Use it when working on the Jamie-BitFlight Claude Skills repository and needing its layout, conventions, or required setup.
Why use it?
It gives agents the project context and operating rules they need before changing or checking the repository.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Jamie-BitFlight/claude_skills's own configuration. It tells Claude Code, Codex and OpenCode how to work on claude_skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude_skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jamie-BitFlight/claude_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/Jamie-BitFlight/claude_skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code, Codex, OpenCode.

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.

agentmods badge for claude_skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jamie-bitflight/claude_skills/agents-md.svg)](https://agentmods.dev/instructions/jamie-bitflight/claude_skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jamie-bitflight/claude_skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jamie-bitflight/claude_skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,804 This file is loaded in full into every session.
When invoked 2,804 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02804 $0.02804
Opus 5 $0.01402 $0.01402
Sonnet 5 $0.00561 $0.00561
Haiku 4.5 $0.00280 $0.00280

Measured yesterday against content hash c129927449de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude_skills AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

8. **Bounded subprocess execution**: `scripts/run_bounded.py` runs a command with a timeout and terminates its full process group (POSIX process-group signals; `taskkill /T /F` on Windows) on expiry, including descendant
AGENTS.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Agent Working Guide for claude_skills

Evidence Proportionality

Before using tools, running tests, searching history, or gathering evidence, ask: Could the result materially change the decision, recommendation, or action? If not, skip that work; if uncertain, prefer the cheapest evidence that can resolve the uncertainty rather than maximizing information.

Repository Overview

Project: Claude Code Marketplace Plugin Collection — marketplace name jamie-bitflight-skills, defined in .claude-plugin/marketplace.json. Most entries are local directories under plugins/. The rest are external: the upstream astral plugin pinned by git-subdir, and hallucination-detector from a sibling GitHub repo. Read the manifest for the current roster. Purpose: Extends Claude Code CLI (and secondarily Codex, OpenCode, and GitHub's coding agent) with specialized skills, commands, and agents for Python development, code quality, Git/CI-CD, AI/LLM tools, documentation, and agent orchestration. Languages: Markdown (skills/commands/agents), Python 3.11+ (scripts; .python-version pins 3.13), JavaScript/TypeScript (hooks, MCP scripts) Package Manager: uv (Astral) — all Python commands use uv run prefix Python Version: 3.11+ required

The largest plugin is plugins/development-harness (install name dh) — the SAM 7-stage pipeline with its own MCP servers (backlog_core/, sam_schema/), agents, and skills. It has its own AGENTS.md; read it before working inside that directory.

Backlog backend for this checkout: GitHub Issues (.dh/config.yaml's backend.name: github). This repo does not use Beads (bd) for task tracking. Never run bd init or bd setup at the repo root. If a Beads integration block reappears in this file, delete it — it does not describe this checkout. See plugins/development-harness/AGENTS.md's "Backend Providers" section for the backend abstraction's Protocol architecture when extending or modifying dh's backend code.

Read the full file on GitHub · 179 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 Changed · -444 lines · -6,643 tokens per session c129927449de
  2. 3d ago First seen · 623 lines · 9,447 tokens per session scan A e2316f2d3cff

Subscribe to this mod's changes

claude_skills AGENTS.md is an instructions file published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed today), licensed MIT. It adds 2,804 tokens to every session, about $0.0140 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other instructions, from other repositories

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

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

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens