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/mgratzer/bloomery/agents-mdgit clone --depth 1 https://github.com/mgratzer/bloomeryWhat 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 | $0.00922 | $0.00922 |
| Opus 5 | $0.00461 | $0.00461 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
bloomery 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bloomery Skill
An agent skill that teaches engineers how to build a coding agent from scratch using raw HTTP calls.
Project Structure
skills/bloomery/
├── SKILL.md # Core skill logic (philosophy, rules, step dispatch)
├── scaffold.sh # Project scaffolding (copies templates, substitutes placeholders)
├── detect.sh # Progress detection (which step the user is on)
├── progress-update.sh # Progress file updates
├── templates/ # Standalone scaffold templates per language
│ ├── typescript/ # agent.ts, .gitignore, AGENTS.md
│ ├── python/ # agent.py, .gitignore, AGENTS.md
│ ├── go/ # main.go, go.mod, .gitignore, AGENTS.md
│ └── ruby/ # agent.rb, .gitignore, AGENTS.md
├── references/
│ ├── curriculum.md # 8-step curriculum (provider-agnostic)
│ ├── providers/
│ │ ├── gemini.md # Gemini API wire format, auth, examples
│ │ ├── openai.md # OpenAI (+ compatible) wire format, auth, examples
│ │ └── anthropic.md # Anthropic wire format, auth, examples
│ └── languages/
│ ├── typescript.md # TS runtime, stdlib, starter code
│ ├── python.md # Python runtime, stdlib, starter code
│ ├── go.md # Go runtime, stdlib, starter code
│ └── ruby.md # Ruby runtime, stdlib, starter code
├── tests/ # BATS test suite (scaffold, detect, progress-update)
│ ├── helpers/common.bash # Shared setup/teardown and fixture helpers
│ ├── scaffold.bats # 25 tests for scaffold.sh
│ ├── detect.bats # 35 tests for detect.sh
│ └── progress-update.bats # 13 tests for progress-update.sh
AGENTS.md # Agent instructions for contributing
README.md # User-facing docs, install instructions
LICENSE # MIT
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.
- 2d ago First seen · 70 lines · 922 tokens per session scan A 3fe7a7bd5d66
bloomery AGENTS.md is an instructions file published in the GitHub repository mgratzer/bloomery (30 stars, last pushed 6mo ago), licensed MIT. It adds 922 tokens to every session, about $0.0046 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
n8n-skills CLAUDE.md
Instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.