Forge-Agentic-Coding-CLI CLAUDE.md

A project instruction file that gives coding agents the repository’s structure, rules, and standard commands. It also points to project-specific workflows and supporting agents.

In plain words
What is it for?
Use it to guide work on the Forge repository, including testing, debugging, adding tools or providers, and release checks.
Why use it?
It keeps the agent from having to rediscover project conventions and helps it verify changes correctly.

Instructions file

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/hoangsonww/forge-agentic-coding-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLI
Per session 1,987 This file is loaded in full into every session.
When invoked 1,987 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 $0.01987 $0.01987
Opus 5 $0.00993 $0.00993
Sonnet 5 $0.00397 $0.00397
Haiku 4.5 $0.00199 $0.00199

Measured 2d ago against content hash 1104d98f6585, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Forge-Agentic-Coding-CLI 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 · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project-specific context for Claude Code (and compatible Claude-based coding agents) working on the Forge repository.

If you're a human reader, the real docs are in README.md, docs/ARCHITECTURE.md, and docs/SETUP.md. This file exists so automated agents don't re-learn the repo on every turn.

Claude-specific tooling lives in .claude/:

  • .claude/settings.json — safe Bash allowlist, deny rules for destructive commands, status line.
  • .claude/rules/*.md — path-scoped rules that only load when Claude reads matching files (TypeScript, testing, tools, models, security, UI).
  • .claude/skills/ — invocable workflows: /verify, /add-tool, /add-provider, /add-agent, /debug-loop, /release-check.
  • .claude/agents/ — subagents with isolated context: code-reviewer, test-runner, docs-auditor.
  • .claude/commands//metrics, /fix-issue.

Use /verify before claiming any change done. Delegate reviews to the code-reviewer subagent so full diffs don't pollute the main context.

Agentic Coding Flywheel. For any non-trivial change, work in plan space → bead space → code space (see FLYWHEEL.md). Skills: /flywheel (overview), /plan, /plan-synthesize, /plan-to-beads, /polish-beads (4–6×), /fresh-eyes, /dedupe-beads, /idea-wizard, /deep-review, /reality-check, /landing, /de-slopify. Subagents: bead-polisher, plan-synthesizer, skill-refiner. Task graph lives in .beads/beads.jsonl; plans in .flywheel/plans/.

When confused after a compaction: "Reread AGENTS.md, CLAUDE.md, and FLYWHEEL.md so they're still fresh in your mind."


Identity of this repo

Forge — a local-first, multi-agent, programmable software-engineering CLI runtime. Written in TypeScript, targets Node 20+. Ships as:

  • @hoangsonw/forge (npm)
  • ghcr.io/hoangsonw/forge-agentic-coding-cli (Docker image, multi-arch)
  • docker/docker-compose.yml for the full stack with Ollama + UI

Read the full file on GitHub · 180 lines

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 · 180 lines · 1,987 tokens per session scan A 1104d98f6585

Subscribe to this mod's changes

Forge-Agentic-Coding-CLI CLAUDE.md is an instructions file published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (22 stars, last pushed 16d ago), licensed MIT. It adds 1,987 tokens to every session, about $0.0099 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.