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/hoangsonww/forge-agentic-coding-cli/agents-mdgit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLIWhat 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 | $0.02033 | $0.02033 |
| Opus 5 | $0.01017 | $0.01017 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
Forge-Agentic-Coding-CLI AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project-wide guidance for any code-writing agent (Codex, OpenAI agent runtime, Cursor, Aider, Cline, Continue, …). Claude Code reads this too but also reads CLAUDE.md.
Tooling infrastructure. On top of this file, the repo ships agent-specific wiring so every major coding agent has the same rules, skills, and permissions:
.claude/— Claude Code settings, path-scoped rules, skills (/verify,/add-tool,/add-provider,/add-agent,/debug-loop,/release-check), subagents (code-reviewer,test-runner,docs-auditor), and safe/deny permissions..codex/— Codexconfig.toml, execpolicyrules/default.rules, custom agents (forge_explorer,forge_reviewer,forge_test_runner), guardrail hooks, and Codex-native skills..cursor/rules/— Cursor*.mdcrules (always-applied core + path-scoped TypeScript/testing/tools/models/security/UI rules)..agents/skills/— portable skills following the open agentskills.io spec. Any compliant agent can read these without vendor-specific wiring.If you update a workflow (e.g. the verify chain), update it in
.agents/skills/verify/SKILL.mdfirst, then mirror the change into.claude/skills/verify/SKILL.mdand.codex/skills/verify/SKILL.mdif they diverge.Agentic Coding Flywheel. Forge follows a plan-heavy, bead-driven workflow for any non-trivial change. See FLYWHEEL.md for the full methodology. In brief:
- Plan space →
.flywheel/plans/(iterated markdown plans)- Bead space →
.beads/beads.jsonl(self-contained work units)- Code space →
src/+test/(implementation)Skills:
/plan,/plan-synthesize,/plan-to-beads,/polish-beads(run 4–6×),/fresh-eyes,/dedupe-beads,/idea-wizard,/deep-review,/reality-check,/landing,/de-slopify. Subagents:bead-polisher,plan-synthesizer,skill-refiner(Claude);forge_bead_polisher,forge_plan_synthesizer(Codex). The 8 canonical operators live in.flywheel/operators/.Post-compaction ritual. When an agent gets confused, send: "Reread AGENTS.md, CLAUDE.md, and FLYWHEEL.md so they're still fresh in your mind." This is the single most common intervention in the methodology.
Conform to the OpenAI
AGENTS.mdconvention: this file is a flat Markdown cheat-sheet that answers the questions "where am I, what can I run, and what shouldn't I break?".
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.
- 2d ago First seen · 191 lines · 2,033 tokens per session scan A 0aa42eec8a59
Forge-Agentic-Coding-CLI AGENTS.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 2,033 tokens to every session, about $0.0102 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
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
skillspec CLAUDE.md
Claude Code instructions for e01n0/skillspec, covering skillspec, build & test, architecture, adding a language feature and adding a cli command.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.
moo-tasks AGENTS.md
Instructions for dizlexic/moo-tasks, covering agents.md, 1. what is the moo tasks board?, 2. connecting your agent, 3. available mcp tools and 4. recommended workflow for agents.
pi CLAUDE.md
Instructions for share-skills/pi, covering 强制, 内部目标（不可写入公开文件）, 跑分规范 and eval 驱动优化规则.