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/gyuha/forge/claude-mdgit clone --depth 1 https://github.com/gyuha/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/gyuha/forge/claude-md)<a href="https://agentmods.dev/instructions/gyuha/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/gyuha/forge/claude-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 | $0.16512 | $0.16512 |
| Opus 5 | $0.08256 | $0.08256 |
| Sonnet 5 | $0.03302 | $0.03302 |
| Haiku 4.5 | $0.01651 | $0.01651 |
Grade A, and why
forge CLAUDE.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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**배포 후 "설치 테스트":** `/plugin install`·`/plugin marketplace update`는 interactive 명령이라 에이전트가 실행 못 한다(사용자가 직접 침). 에이전트가 검증할 수 있는 건 설치 전제뿐 — `curl -fsSL raw.githubusercontent.com/gyuha/forge/main/.claude-plugin/{plugin,market The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- today Changed · +7 lines · +1,117 tokens per session 545e97338147
- 3d ago First seen · 178 lines · 15,395 tokens per session scan A 07f61eefa490
forge CLAUDE.md is an instructions file published in the GitHub repository gyuha/forge (4 stars, last pushed today), with no licence file. It adds 16,512 tokens to every session, about $0.0826 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
superpowers GEMINI.md
Gemini CLI instructions for obra/superpowers, a project described as: An agentic skills framework & software development methodology that works.
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
cli copilot-instructions.md
Instructions for semanticash/cli: Review pull requests for correctness, regressions, and missing tests before style concerns.
scaffold GEMINI.md
Instructions for victusfate/scaffold: Follow all guidelines in AGENTS.md at the project root.
specship CLAUDE.md
Instructions for bonnguyenitc/specship, covering specship — dev guide, verify every change and learnings.