Borrowing it
Nothing to install: this file belongs to mathomhaus/guild. 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/mathomhaus/guild/main/AGENTS.mdgit clone --depth 1 https://github.com/mathomhaus/guildWrote 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/mathomhaus/guild/agents-md)<a href="https://agentmods.dev/instructions/mathomhaus/guild/agents-md"><img src="https://agentmods.dev/badge/instructions/mathomhaus/guild/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/mathomhaus/guild/agents-md"><img src="https://agentmods.dev/badge/instructions/mathomhaus/guild/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 | $0.00700 | $0.00700 |
| Opus 5.5 | $0.00280 | $0.00280 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
guild 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 19d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guild — agent bootstrap
This is the source repo for the guild binary. The MCP server's
INSTRUCTIONS string (loaded when an MCP client connects to guild)
carries the full operating contract — tool discipline, kind taxonomy,
autonomy rules, narration. This file only adds repo-specific context
for contributors.
First action — bootstrap guild MCP
mcp__guild__guild_session_start(project="guild")
Surfaces the last briefing + oath + top bounty for work on this repo.
Every subsequent guild MCP tool inherits project="guild" automatically.
Repo facts
- Module:
github.com/mathomhaus/guild - Language: Go 1.26.9+
- Main libs:
spf13/cobra,log/slog,modernc.org/sqlite(pure-Go),github.com/modelcontextprotocol/go-sdk(version: see go.mod) - Entry points:
cmd/guild/main.go,cmd/sqlcheck/main.go - Test gate:
make check(fmt + vet + lint + sqlcheck + test-race) - CI reproducer:
make ci - Release: goreleaser via
make release-snapshotlocally or v*.. tag push
Tool discipline
- Use guild MCP tools (
mcp__guild__*) for all guild operations - Bash CLI (
guild lore ...,guild quest ...) only as last resort if MCP is unrecoverable - Never bypass the tool to write raw SQL against
~/.guild/*.db
When onboarding
Contributors new to the repo should also skim:
README.md— install + setup from an end-user perspectiveMakefile— the canonical developer commands (make helpfor the list)internal/mcp/instructions.go— the constant string every MCP client reads on connect
guild workflow
guild coordinates tasks (quest) and persistent knowledge (lore) across sessions and agents.
BEFORE ANY OTHER ACTION — before reading files, editing code, or
responding to the user — call the MCP tool guild_session_start(project="guild").
It returns the full agent contract, active principles (oath), and the
current top bounty. Follow what it returns.
If guild_session_start is not visible in your tool list, run your
host's tool-search for guild first — some hosts lazy-load MCP tools.
Do NOT fall back to CLI; the MCP server is available.
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.
- 19d ago Changed · +2 tokens per session b99b200128dc
- 1mo ago First seen · 69 lines · 698 tokens per session scan A 5278fb2a2b8f
guild AGENTS.md is an instructions file published in the GitHub repository mathomhaus/guild (302 stars, last pushed yesterday), licensed Apache-2.0. It adds 700 tokens to every session, about $0.0028 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 2026-08-30.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.