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/kerbelp/metatron/agents-mdgit clone --depth 1 https://github.com/kerbelp/metatronWrote 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/kerbelp/metatron/agents-md)<a href="https://agentmods.dev/instructions/kerbelp/metatron/agents-md"><img src="https://agentmods.dev/badge/instructions/kerbelp/metatron/agents-md.svg" alt="Measured on agentmods" 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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
metatron 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Ground rules for working in this repo. Read this first.
What Metatron is
Metatron is a self-hosted system that captures a company's real implementation decisions — preferred patterns, rejected approaches, edge cases, internal conventions — as structured decisions, and serves them to coding agents over MCP (Model Context Protocol). The goal is for an agent to write code like a senior engineer who already knows this codebase. It runs against a private codebase, so assume sensitive data and on-prem deployment.
Tech stack (decided — not open for debate)
These are locked. Do not re-litigate or substitute them:
- Python 3.12+
- Official MCP Python SDK for the server
- tree-sitter for language-agnostic code parsing
- SQLite for the decision store — but always behind a storage interface, because the schema must be portable to Postgres later
- pytest for tests
- uv for dependency management
Core principle
- Decisions are stored as structured records (fields: pattern, context/scope, rationale, confidence, source refs) — never as prose specs.
- Nothing enters the canonical set without human curation. No decision self-promotes. Human-in-the-loop is by design, not a temporary shortcut.
Workflow
- All changes go through a pull request, then merge to main.
- No direct commits to main.
- Keep PRs small and reviewable, and each PR includes tests.
- Before starting any work, read
docs/anddocs/incidents/(they may not exist yet — if so, note that and proceed).
Scope discipline
Architectural doors stay open for these, but build none of them yet:
- Self-improving / automatic-feedback loop
- Telemetry ingestion
- Auth, multi-tenant, RBAC, and any hosted/multi-user web app
- Jira / ticket / postmortem ingestion (a later source)
- Postgres (use SQLite now, behind the storage interface)
- Deployment infra and packaging for distribution
A local, single-user curation web UI (metatron ui, bound to localhost) is
in scope — it's a thin local view over the same DecisionStore the CLI uses. The
out-of-scope item is a hosted/multi-user web app with auth, not this.
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.
- 3d ago First seen · 76 lines · 806 tokens per session scan A 8c53588941d1
metatron AGENTS.md is an instructions file published in the GitHub repository kerbelp/metatron (24 stars, last pushed 1mo ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-08-30.
Other instructions, from other repositories
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
thinkrail CLAUDE.md
Instructions for JetBrains/thinkrail, a project described as: Vibe code with pi in a lightweight, real IDE - The Vibe You Need.
agent-rules testing.instructions.md
Instructions for lirantal/agent-rules, covering testing guidelines for node.js applications, general testing principles, guiding principles, descriptive test naming (three-part structure) and structure tests by the aaa pattern.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
bdb-dev-optimized-agent-skills CLAUDE.md
Instructions for hybridlabor-api/bdb-dev-optimized-agent-skills, covering bdb agent skills — global instructions, docs & pipeline, how many agents, safety gate — mechanically enforced, not advisory and non-negotiable.