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/firatcand/forge/claude-mdgit clone --depth 1 https://github.com/firatcand/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/firatcand/forge/claude-md)<a href="https://agentmods.dev/instructions/firatcand/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/firatcand/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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
forge 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 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.
What it actually says
This project uses Forge. The methodology below is imported from a local file regenerated by
forge upgrade. New collaborator? Install Forge with:npm install -g @firatcand/forge forge upgradeFirst time opening this repo in Claude Code? You'll see a one-time prompt asking permission to load
.forge/CONTEXT.md. Accept it — without that approval, Claude Code silently skips the import and the methodology context won't be available.
@.forge/CONTEXT.md
The import below pulls in THIS project's spec — the synthesized BRIEF/PRD/SPEC (the "what", vs. the methodology "how" above). It is committed and generated by
/ingest-spec(a stub until you run it), so it travels with the repo.
@spec/CONTEXT.md
forge
Note: This is the forge repo itself. Iterating on this repo means iterating on the framework — every change ships to
npm publish @firatcand/forgeand lands on adopter machines vianpx @firatcand/forge. Treat all changes as public-API.
Stack
Commands
- Build:
npm run build - Test:
npm test - Type check:
npm run typecheck - Lint:
npm run lint(ESLint — unused vars/imports + unreachable; non-blocking, warnings only) - Dev:
npm run dev - Render methodology context (one-shot, until Phase B's
forge upgradeships):npm run forge:render-context
Conventions
- Functional components only, no class components
- Always handle errors explicitly — no silent catches
- New API routes must have input validation
- See
spec/for full conventions
Critical paths
See CRITICAL.md
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 · 50 lines · 463 tokens per session scan A e7ee7aa08f15
forge CLAUDE.md is an instructions file published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 463 tokens to every session, about $0.0023 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
prospec AGENTS.md
AGENTS.md instructions for benwu95/prospec, covering prospec, tech stack, language policy, core resources and constitution.
prospec CLAUDE.md
Claude Code instructions for benwu95/prospec, covering prospec, tech stack, language policy, core resources and constitution.
nextjs-loop-engineering-starter AGENTS.md
Instructions for muzafferkadir/nextjs-loop-engineering-starter, covering agents.md — project instructions for ai agents, how to start a loop, project purpose, stack and commands.
odin-codex-plugin AGENTS.md
AGENTS.md instructions for OutlineDriven/odin-codex-plugin, covering codex coding agent adherences, token-efficient cli output, tool hierarchy, core system & file ops and search & discovery.
baro AGENTS.md
AGENTS.md instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.
baro CLAUDE.md
Claude Code instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.