seeds AGENTS.md

Project-specific instructions for AI coding agents working on Seeds, a Git-based issue tracker whose data is stored in text files. They describe the project, tools, layout, and commands.

In plain words
What is it for?
Use them when working on Seeds to find the right files, understand its Bun-based setup, and run the expected commands safely.
Why use it?
They give an agent the key project context and working rules at the start of a session, reducing guesswork about how to build, test, and change the code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/jayminwest/seeds/agents-md
Clone the repo
git clone --depth 1 https://github.com/jayminwest/seeds

Made for: Codex, OpenCode.

Per session 2,833 This file is loaded in full into every session.
When invoked 2,833 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02833 $0.02833
Opus 5 $0.01417 $0.01417
Sonnet 5 $0.00567 $0.00567
Haiku 4.5 $0.00283 $0.00283

Measured 3d ago against content hash b51b2317037a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seeds 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.

AGENTS.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the canonical entry point for AI coding agents working in the seeds repo, following the agents.md convention. It is intentionally short and command-focused: read it at session start to know how to build, test, and ship. CLAUDE.md is the long-form authoritative companion — when the two disagree, CLAUDE.md wins and this file should be updated to match.

What this project is

Seeds is a git-native issue tracker for AI agent workflows. The JSONL file IS the database: there is no binary store, no export pipeline, no separate sync daemon. All issues live in .seeds/issues.jsonl (one JSON object per line), templates in .seeds/templates.jsonl, plans in .seeds/plans.jsonl, and project config in .seeds/config.yaml. Files are diffable, mergeable (merge=union gitattribute + dedup-on-read), and edited only through the sd CLI, which holds advisory file locks so parallel agents never corrupt the store.

Seeds is part of the os-eco ecosystem alongside warren (control plane), burrow (sandbox), plot (coordination), mulch (expertise), and canopy (prompts). See SPEC.md for the V1 design record.

Tech stack at a glance

  • Runtime: Bun (runs TypeScript directly; no build step).
  • Language: TypeScript, strict mode (noUncheckedIndexedAccess, no any).
  • Lint / format: Biome (biome.json) — tab indentation, 100-char line width, errors fail CI.
  • Tests: bun test, Jest-compatible API, real I/O over temp dirs (no mocks). Tests are *.test.ts co-located with the file under test.
  • Storage: JSONL under .seeds/; minimal built-in YAML parser (src/yaml.ts) for config.
  • CLI: sd, defined in src/index.ts and dispatched via commander.

Project layout

seeds/
├── src/
│   ├── index.ts            # sd CLI entry point + command router
│   ├── version.ts          # VERSION constant (import without CLI side-effects)
│   ├── types.ts            # Issue, Template, Config, shared constants
│   ├── store.ts            # JSONL read/write/lock/atomic-rename
│   ├── id.ts               # ID generation ({project}-{4hex})
│   ├── config.ts           # YAML config load/save
│   ├── output.ts           # JSON + human output helpers
│   ├── yaml.ts             # minimal flat YAML parser
│   └── commands/           # one file per subcommand (create, ready, plan, …)
├── scripts/                # quality-gate scripts + budgets
│   ├── validate-agents-md.ts   # validates this file's references
│   ├── check-file-sizes.ts
│   ├── check-debt-markers.ts
│   ├── check-coverage.ts
│   ├── report-test-timing.ts
│   ├── report-quality-metrics.ts
│   └── version-bump.ts
├── .seeds/                 # seeds dogfoods seeds (its own issue store)
├── .factory/skills/        # repo-local agent skills
├── .github/workflows/      # ci.yml + publish.yml + auto-merge.yml
├── CLAUDE.md               # authoritative long-form agent doc
├── RUNBOOK.md              # release / triage / rollback procedures
├── SPEC.md                 # V1 design record
├── README.md               # user-facing pitch
├── CHANGELOG.md            # release history
├── biome.json
├── tsconfig.json
└── package.json

Read the full file on GitHub · 252 lines

Changes

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.

  1. 3d ago First seen · 252 lines · 2,833 tokens per session scan A b51b2317037a

Subscribe to this mod's changes

seeds AGENTS.md is an instructions file published in the GitHub repository jayminwest/seeds (131 stars, last pushed 15d ago), licensed MIT. It adds 2,833 tokens to every session, about $0.0142 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens