Borrowing it
Nothing to install: this file belongs to harshanandak/forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/harshanandak/forge/main/AGENTS.mdgit clone --depth 1 https://github.com/harshanandak/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/harshanandak/forge/agents-md)<a href="https://agentmods.dev/instructions/harshanandak/forge/agents-md"><img src="https://agentmods.dev/badge/instructions/harshanandak/forge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/harshanandak/forge/agents-md"><img src="https://agentmods.dev/badge/instructions/harshanandak/forge/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00491 | $0.00491 |
| Opus 5.5 | $0.00196 | $0.00196 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
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 today.
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.
What it actually says
Forge
Forge (npm package forge-workflow, command forge) is an open building-block platform for AI coding agents. Blocks declare their operations once; the CLI and MCP tools are generated from that catalog. Core knows no workflow: stages, TDD and pull requests live in blocks and templates. Bun builds Forge; the published package runs on Node 24.15 or later 24.x, or Node 26 and later (Node 25 is not supported) with npm and assumes nothing about a user's toolchain.
Commands: package.json scripts. test/structure holds repo guards.
Agents: use forge <noun> <verb> --help --json or forge catalog describe <noun.verb> for the full JSON contract.
Gotchas
bun lintneeds canary;bun fmtis stable in 1.4.4. Thelintandfmtscripts usetools/bun-builtin.ts, which exits 1 with an upgrade hint on a Bun without the built-in.bun checkneeds Bun 1.4.3 or newer.- CI is the gate and there are no local git hooks. Run what you touched locally; the full matrix runs on the pull request. Fix the cause of a failing check; never skip one with
--no-verifyorcore.hooksPathtricks. - Work in a git worktree under
.worktrees/, based on the fetchedorigin/main. - Commit with conventional titles (
feat:,fix:,docs:,chore:,refactor:,test:,ci:). The pull request title is checked and becomes the squash-merge title and the changelog line. - After cloning, run
forge skills sync. People run/forge-loop; models read.agents/skills/forge-loop/SKILL.mdwhen told to. - Checks: PASS exits 0; FAIL 1; INCOMPLETE/NOT_EXECUTED 2. Non-PASS keeps the receipt with
ok:false.
Standards
Read CODING_STANDARDS.md before writing or reviewing code, adding a dependency, adding a test, or retiring something. It holds the boundaries, dependency, test and platform rules; most are enforced by a guard in test/structure.
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.
- today Changed · +6 tokens per session 079aac315fb8
- 2d ago Changed · +1 tokens per session a25312d1d33f
- 8d ago Changed · +1 lines · +36 tokens per session 35314b9b536e
- 9d ago Changed · +2 lines · +33 tokens per session c240bb3787c3
- 11d ago Changed · -357 lines · -5,133 tokens per session b7a48b41d533
- 2mo 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 (0 stars, last pushed yesterday), licensed MIT. It adds 491 tokens to every session, about $0.0020 per session on Opus 5.5. 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 buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.