agentmods.dev

forge CLAUDE.md

A set of instructions that adds a structured planning and checking workflow to Claude Code, a coding assistant.

In plain words
What is it for?
Use it to plan projects, run validation, review completed modules, investigate errors, track progress, and save or recall project memory.
Why use it?
It helps break large objectives into smaller work, check plans and results, retry failed work, and remember lessons between sessions.

Instructions file

35 2mo ago A scan 434 tokens original MIT
View the source file TT-Wang/forge
Install

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.

agentmods
npx agentmods add instructions/tt-wang/forge/claude-md
Clone the repo
git clone --depth 1 https://github.com/TT-Wang/forge
Per session 434 This file is loaded in full into every session.
When invoked 434 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00434 $0.00434
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash 79b64d90c4b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

CLAUDE.md · 48 lines

What it actually says

Forge

Forge is a lightweight workflow layer for Claude Code that adds structured planning, deep validation, retry intelligence, session resumability, and cross-session memory.

Quick Start

/forge <objective>

This triggers the full workflow: understand → plan → validate plan → execute → validate → retry → learn.

Skills

  • /forge <objective> — Full workflow: plan, execute, validate, learn
  • /forge-validate <module-id> — Validate a specific module
  • /forge-status — Show current plan status and memory

Agents

  • planner — Decomposes objectives into module DAGs, validates plan structure
  • worker — Executes a single module in a worktree
  • reviewer — Reviews completed modules for correctness, uses contract checks
  • debugger — Root-cause analysis with structured log inspection

MCP Tools

The forge MCP server provides 7 tools:

  • validate — Run verification commands with syntax checks, API contract verification, stagnation/velocity/oscillation detection
  • validate_plan — Structural plan validation: DAG cycles, file overlaps, command existence, schema checks
  • memory_recall — Search project/global memory
  • memory_save — Save learned patterns
  • iteration_state — Track retry attempts per module
  • forge_logs — Query structured JSONL logs (filter by run, module, phase, severity)
  • session_state — Save/load/list orchestrator state for session resumability

Plugin Structure

This project is a Claude Code plugin. Install with claude plugin add github:TT-Wang/forge.

agents/           — Agent definitions (planner, worker, reviewer, debugger)
skills/           — Skill definitions (/forge, /forge-validate, /forge-status)
forge-mcp-server/ — MCP server (7 tools: validate, validate_plan, memory, iteration, logs, session)
.claude-plugin/   — Plugin manifest (plugin.json)
.forge/           — Runtime data (plans, memory, iterations, logs, state)
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. 2d ago First seen · 48 lines · 434 tokens per session scan A 79b64d90c4b6

Subscribe to this mod's changes

forge CLAUDE.md is an instructions file published in the GitHub repository TT-Wang/forge (35 stars, last pushed 2mo ago), licensed MIT. It adds 434 tokens to every session, about $0.0022 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.

agentanthropicclaudeclaude-codeclaude-code-plugingit-worktree
Related

Other instructions, from other repositories

ii-agent AGENTS.md

Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.

Intelligent-Internet/ii-agent · 3,294 tokens

intelligent-terminal rust.instructions.md

Concise Rust coding conventions for this repository.

microsoft/intelligent-terminal · 435 tokens

sortie copilot-instructions.md

Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).

sortie-ai/sortie · 1,030 tokens

crust AGENTS.md

Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.

chenxin-yan/crust · 388 tokens

she-love-me CLAUDE.md

Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.

863401402/she-love-me · 268 tokens

TuyaOpen AGENTS.md

AGENTS.md instructions for tuya/TuyaOpen, covering agents.md, cursor cloud specific instructions, communication and behavior, environment setup and export progress protocol (ide).

tuya/TuyaOpen · 1,652 tokens