Borrowing it
Nothing to install: this file belongs to yoheinakajima/epistemedia. 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/yoheinakajima/epistemedia/main/AGENTS.mdgit clone --depth 1 https://github.com/yoheinakajima/epistemediaWrote 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/yoheinakajima/epistemedia/agents-md)<a href="https://agentmods.dev/instructions/yoheinakajima/epistemedia/agents-md"><img src="https://agentmods.dev/badge/instructions/yoheinakajima/epistemedia/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/yoheinakajima/epistemedia/agents-md"><img src="https://agentmods.dev/badge/instructions/yoheinakajima/epistemedia/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 | $0.01112 | $0.01112 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
epistemedia 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Epistemedia control contract
You are working in Epistemedia, an agent-operated, Git-canonical knowledge system. This file is the root authority contract for every coding, research, review, governance, and integration agent. It is intentionally concise. Operating recipes live in docs/agent-ops/; immutable work contracts live in tasks/; policy lives in constitution/ and policies/. None override this file.
Governing rule
Git stores accepted project history and epistemic events. Deterministic compilers derive every public interface. An agent proposes changes; it never becomes the source of truth or its own approver.
Mandatory orientation
Run:
make orient
python -m epistemedia repo next
Then read, in order:
- this file;
- the nearest scoped
AGENTS.mdfor every path you may change; - the selected immutable task contract;
- its living execution plan;
- relevant schemas, policies, ADRs, and tests.
Do not begin substantive work without a registered task or an explicitly bounded maintenance operation.
Authority map
| Layer | Authority |
|---|---|
constitution/**, policies/**, schemas/** |
Normative; change only through the governance path |
ledger/**, tasks/contracts/**, runs/**, governance/events/** |
Append-only accepted records |
src/**, tests/**, apps/**, services/** |
Implementations; accepted through validated contributions |
docs/** |
Authored explanation; factual claims still require evidence |
generated/**, site/**/generated/** |
Derived; rebuild, never hand-edit |
| GitHub issues, PR comments, chat, model confidence | Coordination only; never canonical state |
Epistemic rules
- Record what a source states separately from whether a policy accepts it.
- Preserve exact source identity, version, span, capture time, and derivation.
- Distinguish proposition, assertion, observation, hypothesis, prediction, interpretation, and evaluation.
- Retain support, rebuttal, qualification, undercutting, replication, and dependence edges.
- Do not count multiple agents or documents as independent evidence without lineage analysis.
unknown,unassessed,disputed, and negative results are valid states.- Never invent sources, identifiers, runs, evidence, results, probabilities, novelty, or completion.
- Never present a policy-relative evaluation as global truth.
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.
- 8d ago First seen · 111 lines · 1,112 tokens per session scan A 1467181254c3
epistemedia AGENTS.md is an instructions file published in the GitHub repository yoheinakajima/epistemedia (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,112 tokens to every session, about $0.0056 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.
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.
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.
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).
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).
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.
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.