Borrowing it
Nothing to install: this file belongs to monkey1wizard/Golem-Agents-Legion. 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/monkey1wizard/Golem-Agents-Legion/main/AGENTS.mdgit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote 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/monkey1wizard/golem-agents-legion/agents-md)<a href="https://agentmods.dev/instructions/monkey1wizard/golem-agents-legion/agents-md"><img src="https://agentmods.dev/badge/instructions/monkey1wizard/golem-agents-legion/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/monkey1wizard/golem-agents-legion/agents-md"><img src="https://agentmods.dev/badge/instructions/monkey1wizard/golem-agents-legion/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 | $0.03021 | $0.03021 |
| Opus 5.5 | $0.01208 | $0.01208 |
| Sonnet 5.5 | $0.00604 | $0.00604 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
Golem-Agents-Legion 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by
/gal initfor Codex CLI, Copilot CLI, Antigravity workspace rules, remaining Google CLI bridges, and opencode. Do not edit manually.
GAL Agent Instructions
Named Workflow Obedience
Binding. When the user invokes any GAL named workflow — $gal-pipeline, $gal-finalize, $gal-status, $deep-planning, $refining-plan, $plan-to-prompt — or expresses repo-work intent (implement, plan, finalize, review, 實作, 規劃, 跑 pipeline, finalize), your first action MUST be to load and execute the corresponding SKILL.md before taking any action. Generic autonomous coding, batch edits, or a summary response that bypasses the named workflow is a named workflow obedience failure.
Continue Work and Ask Only When Needed
When an authorized step needs no user input, keep going until the requested work is complete or a required GAL gate blocks progress. Put the progress note and the concrete next action in the same update, then take that action. Do not end the turn merely to report progress or ask whether to continue.
Stop and ask only when missing user input prevents progress, before destructive actions such as deleting data or force-pushing, or before modifying files outside this repository. Honor prior explicit authorization within its stated scope. Required GAL approvals, receipt gates, protected-path review, executor custody, working-hours rules, and repository constraints still apply.
Critical Stop Rules
The GAL critical runtime pack — binding stop rules for headless and interactive runs alike:
$gal-pipeline: the first implementation edit is gated ongal pipeline-preflight <prompt> --receipt <path>returningpass— make no edit before that.- When more than one plan is active, require an explicit
'#file:<prompt>'path. Never auto-select the first active-plan row. - If a receipt/log write fails under sandbox denial, STOP and rerun the exact
galcommand after approval — do not fall back to role-playing pipeline phases in chat. - The goal-backward verify pass is orchestrator-owned and always runs in-process. It is never a dispatch phase.
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 · -54 tokens per session ed454202a3f7
- 8d ago Changed · -6 tokens per session 6ec799e41dd6
- 13d ago Changed · +22 lines · +402 tokens per session 3b7cca804041
- 14d ago Changed · +11 lines · +433 tokens per session 4f6289e7fe7b
- 28d ago Changed · +2 lines · +36 tokens per session c4e6eaf7339e
- 1mo ago Changed · +81 tokens per session de8f452144ea
- 1mo ago First seen · 135 lines · 2,129 tokens per session scan A 4b6204d20079
Golem-Agents-Legion AGENTS.md is an instructions file published in the GitHub repository monkey1wizard/Golem-Agents-Legion (14 stars, last pushed yesterday), licensed MIT. It adds 3,021 tokens to every session, about $0.0121 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 2026-09-04.
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.