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/harshanandak/forge/agents-mdgit clone --depth 1 https://github.com/harshanandak/forgeWhat 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 | $0.05548 | $0.05548 |
| Opus 5 | $0.02774 | $0.02774 |
| Sonnet 5 | $0.01110 | $0.01110 |
| Haiku 4.5 | $0.00555 | $0.00555 |
Grade A, and why
forge 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Workflow Instructions
Default TDD-First Workflow Template
This project ships a default TDD-first workflow template with 6 workflow stages plus a composable research skill (a phase of /plan and usable standalone). In v3, these stages are one configurable composition over Forge runtime building blocks, not a product-wide mandatory ladder. Commands may be invoked as full stages or as smaller skill fragments when the active plan permits it. Pre-merge is an embedded gate in /ship and /review (not a numbered stage); /status and /shepherd are utilities (not stages).
Skill Dispatch (auto-trigger)
Before ANY response — including clarifying questions or exploring the codebase — if there is even a 1% chance a Forge skill applies, invoke it, then announce Using [skill] to [purpose]. Invoke the using-forge dispatch skill (auto-discovered from your agent's own skills — Forge setup installs it into each harness's skills dir; it carries the 1%-rule and routing table), or run forge skill for "<situation>" for the deterministic best-fit skill. This is agent-agnostic — never branch on harness identity.
| Stage | Command | Purpose | Required For |
|---|---|---|---|
| 1 | /plan |
Design intent → research → branch + worktree + task list | Critical, Standard, Refactor |
| 2 | /dev |
Subagent-driven TDD per task (spec + quality review) | All types |
| 3 | /validate |
Validate + 4-phase debug mode on failure | All types |
| 4 | /ship |
Create PR with documentation | All types |
| 5 | /review |
Address ALL PR feedback | Critical, Standard |
| 6 | /verify |
Post-merge health check (CI, deployments) | All types |
Pre-merge gate (not a numbered stage): Completing docs on the feature branch and handing off the PR for merge is a task-type gate and checkpoint, not a standalone workflow stage. The gate runs for Critical, Standard, and Refactor work and is embedded in the /ship and /review stages — finish the doc updates, confirm CI is green, then hand off the PR. Simple, Hotfix, and Docs work skip the gate.
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 · 374 lines · 5,548 tokens per session scan A af5d81e9fd89
forge AGENTS.md is an instructions file published in the GitHub repository harshanandak/forge (4 stars, last pushed 3d ago), licensed MIT. It adds 5,548 tokens to every session, about $0.0277 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 2026-08-31.
Other instructions, from other repositories
vscode_abap_remote_fs CLAUDE.md
Instructions for marcellourbani/vscode_abap_remote_fs, covering abap fs development guidelines, workflow and constraints.
sheal AGENTS.md
Instructions for liwala/sheal, covering agent instructions, agent operating policy, 1. tdd discipline — strict order, the only exception: spikes and 2. tests assert intent.
digital-service-orchestra skills.instructions.md
Instructions for navapbc/digital-service-orchestra, a project described as: Workflow infrastructure plugin for Claude Code projects — TDD-driven sprint management, review gates, hook parameterization, and multi-stack config.
spec-driven-tdd AGENTS.md
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
mcp-repo-onboarding AGENTS.md
Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.
arxiv-agent-mcp AGENTS.md
AGENTS.md instructions for tbaraniuk/arxiv-agent-mcp, covering agents.md, roles, test-writer, implementer and per-task loop.