fulcrum: Instructions file for Claude Code

AGENTS.md

fulcrum AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from moabualruz/fulcrum. It costs 5,696 tokens per session, scanned A, original, MIT.

Project instructions for Fulcrum, a local command-line system for supervising coding agents, repositories, tasks, and related files. They describe its current foundation, including hooks and support for several agent tools.

In plain words
What is it for?
Use them when working on Fulcrum’s command-line tool, agent integrations, hooks, shared rules, skills, package handling, or tool-output policies.
Why use it?
They tell an agent what Fulcrum currently does and which project boundaries to respect while the system is being built.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is moabualruz/fulcrum's own configuration. It tells Claude Code, Codex and OpenCode how to work on fulcrum itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fulcrum configures →

Reuse

Borrowing it

Nothing to install: this file belongs to moabualruz/fulcrum. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/moabualruz/fulcrum/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/moabualruz/fulcrum

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for fulcrum AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/moabualruz/fulcrum/agents-md.svg)](https://agentmods.dev/instructions/moabualruz/fulcrum/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/moabualruz/fulcrum/agents-md"><img src="https://agentmods.dev/badge/instructions/moabualruz/fulcrum/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,696 This file is loaded in full into every session.
When invoked 5,696 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 5.1 $0.05696 $0.05696
Opus 5 $0.02848 $0.02848
Sonnet 5 $0.01139 $0.01139
Haiku 4.5 $0.00570 $0.00570

Measured 6d ago against content hash ada99aadea0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fulcrum 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 6d 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.

AGENTS.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fulcrum - AGENTS.md

Project-level instructions for any agent (or human) working in this repo.

What Fulcrum is becoming

Fulcrum is a local-first CLI Agent OS for supervising repositories, tasks, agent runs, context, memory, and artifacts.

That destination. Current main = foundation work: cross-agent install layer, hook plumbing, skills, rules, output policy, component lifecycle, package mirrors, MCP registry, CLI orchestrator everything else sit on top of. Mile zero of long road; every commit advance foundation, not jump ahead.

Where we are right now (foundation)

Current main foundation includes:

  • One Bun-compiled fulcrum binary, eight hook subcommands (format, lint-gate, pm-policy, test-on-edit, audit-log, index-check, index-rebuild, tool-output-router).
  • Orchestrator (fulcrum init / install / hooks / skills / doctor / compress) wires hooks into five agent runtimes (Claude Code, Codex CLI, Gemini CLI, OpenCode, Pi CLI).
  • Central rule index installed once under ~/.fulcrum/rules/, with per-agent loader blocks for cross-agent rules distribution.
  • Per-tool output-handling policy (config/tool-output-policy.toml) drives tool-output-router hook.
  • 29 in-repo skills caveman-compressed (.original.md beside each), 20-entry trigger evals each, content-verified against upstream sources.
  • src/agents/registry.ts - canonical Agent interface + AGENTS[5] array; single source of truth consumed by install, doctor, skills. No more inline agent configs scattered across files.
  • fulcrum install --profile minimal|rules-only|full --dry-run support; fulcrum doctor --json for machine-readable health output.
  • bun run compress (apps/cli/src/compress.ts) - idempotent caveman compression of in-repo content; --check for CI.
  • Local CI runner (bun run ci) - 6 stages: install / typecheck / test / build:all / skills:lint / compress:check (hard gate). Local release runner (bun run release vX.Y.Z). fulcrum doctor shows caveman defaultMode, per-agent install state, MCP health, skill metadata budget, and ignored project worktree warnings. Skills lint enforces rules ≤ 200 lines. CHANGELOG via git-cliff.

Read the full file on GitHub · 148 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. 6d ago First seen · 148 lines · 5,696 tokens per session scan A ada99aadea0f

Subscribe to this mod's changes

fulcrum AGENTS.md is an instructions file published in the GitHub repository moabualruz/fulcrum (3 stars, last pushed 2mo ago), licensed MIT. It adds 5,696 tokens to every session, about $0.0285 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens