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/lucasduys/forge/claude-mdgit clone --depth 1 https://github.com/LucasDuys/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/lucasduys/forge/claude-md)<a href="https://agentmods.dev/instructions/lucasduys/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/lucasduys/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 | $0.02828 | $0.02828 |
| Opus 5 | $0.01414 | $0.01414 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge — Autonomous Agent Coding System
What This Is
Forge is a Claude Code CLI plugin that provides an autonomous, spec-driven development loop.
Three commands: /forge brainstorm, /forge plan, /forge execute — they chain together
to take an idea from concept to working code with minimal human intervention.
Project Structure
forge/
├── .claude-plugin/plugin.json — Plugin manifest
├── commands/ — Slash commands (/forge brainstorm, plan, execute, etc.)
├── skills/ — Procedural workflows + cross-cutting skills (guardrails, graphify, design-system)
├── agents/ — Specialized subagents (speccer, planner, executor, reviewer, verifier, researcher)
├── hooks/ — Stop hook (loop engine), token monitor (PostToolUse)
├── scripts/ — JS utility (forge-tools.cjs) + bash helpers
├── templates/ — Output file templates (spec, plan, state, summary)
├── references/ — Reference docs (token profiles, backprop patterns, multi-repo, etc.)
└── docs/superpowers/specs/ — Design specs for this project
Workflow Enforcement (CRITICAL)
The Forge workflow is strictly sequential: brainstorm -> plan -> execute. This is enforced at multiple levels:
- Spec approval gate: Only the brainstorming skill writes
status: approvedspecs, and only after explicit user approval of an approach. The execute command validates this. - Frontier requirement:
/forge executevalidates that every approved spec has a corresponding frontier file from/forge plan. - Programmatic validation:
forge-tools.cjs setup-staterunsvalidateWorkflowPrerequisites()which checks spec approval status and frontier existence before allowing execution. - State machine phases:
brainstormingandplanningare formal phases in the state machine (seereferences/state-machine.md).
Never skip brainstorming. Even if the user's request seems clear, the interactive Q&A surfaces hidden assumptions, the approach proposals prevent over-engineering, and the approved spec provides verifiable acceptance criteria for the reviewer and verifier.
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 · 207 lines · 2,828 tokens per session scan A bce64c516cd9
forge CLAUDE.md is an instructions file published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 2,828 tokens to every session, about $0.0141 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
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.
skillsync-mcp CLAUDE.md
Instructions for adityasugandhi/skillsync-mcp, covering claude.md, project overview, development commands, architecture and key files.