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/seed-hypermedia/seed/agents-mdgit clone --depth 1 https://github.com/seed-hypermedia/seedWhat 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 | $0.01627 | $0.01627 |
| Opus 5 | $0.00813 | $0.00813 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
seed 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Usage Model
- Read this file first.
- Read subtree
AGENTS.mdfiles only when writing files in their scope, or when local behavior is unclear or confusing. - Read
AGENTS.local.mdfiles if they exist. These are local instructions not checked into the repo. They have precedence over other instructions.
Subtree AGENTS.md Map
backend/AGENTS.mdforbackend/**.backend/storage/AGENTS.mdforbackend/storage/**.frontend/AGENTS.mdforfrontend/**.proto/AGENTS.mdforproto/**.vault/AGENTS.mdforvault/**.agents/AGENTS.mdforagents/**.
Agent Assets
- Keep durable repo instructions in
AGENTS.mdand subtreeAGENTS.mdfiles. - Keep reusable workflows and task-specific expertise in repo-local
.agents/skills/so they can be shared by the team. - Keep provider-specific folders such as
.cursor/and.codex/as thin adapters only; do not duplicate canonical instructions there. - Do not rely on personal home-directory skills such as
~/.agents/skillsfor team workflows.
Repo Rules
- Use
pnpmfor main repo,bunforvault/**. - Code inside
ops/**uses a pinned Bun version (seeops/package.jsonengines.bun). Always buildops/dist/deploy.jswith that exact version (bunx --bun bun@<version> build ...) or CI will fail the staleness check. - Code under
backend/util/llama-go/llama.cppis vendored third-party code. Don't touch unless explicitly asked. - Never modify the
.gitdirectory directly. - Do not run git commands that write state, including commit, amend, rebase, reset, checkout, merge, cherry-pick, stash, tag, branch deletion, or push, unless explicitly asked.
- If you need to write a commit message, explain why the change was made, not what the commit is doing mechanically.
Security audit
- The vulnerability-hunting protocol is
docs/security/auditor.md. It is plain markdown and self-contained: point any model at it, or symlink it into a provider's agent directory to launch it as a named agent (for Claude Code:ln -s ../../docs/security/auditor.md .claude/agents/security-auditor.md). - Read
docs/security/audit-log.mdbefore any security review. It records which surfaces have been audited and which hypotheses were ruled out, so sessions resume instead of rediscovering. - Fixed vulnerabilities are disclosed as GitHub issues closed by their fix commit. Detail for unfixed findings stays in
.ai/security/queue.md, which is gitignored — this repo is public.
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.
- 2d ago First seen · 107 lines · 1,627 tokens per session scan A 779675ccf7f8
seed AGENTS.md is an instructions file published in the GitHub repository seed-hypermedia/seed (56 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,627 tokens to every session, about $0.0081 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
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).
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.