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/jayminwest/seeds/claude-mdgit clone --depth 1 https://github.com/jayminwest/seedsWrote 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/jayminwest/seeds/claude-md)<a href="https://agentmods.dev/instructions/jayminwest/seeds/claude-md"><img src="https://agentmods.dev/badge/instructions/jayminwest/seeds/claude-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 | $0.05672 | $0.05672 |
| Opus 5 | $0.02836 | $0.02836 |
| Sonnet 5 | $0.01134 | $0.01134 |
| Haiku 4.5 | $0.00567 | $0.00567 |
Grade A, and why
seeds CLAUDE.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 5d 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seeds
Git-native issue tracker for AI agent workflows. Minimal dependencies, JSONL storage, Bun runtime. Replaces beads in the overstory/mulch ecosystem.
The JSONL file IS the database. No binary files, no export pipeline, no sync step. One file, diffable, mergeable.
Tech Stack
- Runtime: Bun (runs TypeScript directly, no build step)
- Language: TypeScript with strict mode (
noUncheckedIndexedAccess, noany) - Linting: Biome (formatter + linter in one tool)
- Runtime dependencies: chalk, commander (plus Bun built-in APIs:
Bun.file,Bun.write,node:fs,node:crypto) - Dev dependencies:
@types/bun,typescript,@biomejs/biome - Storage: JSONL (git-native, diffable, mergeable)
- Config: YAML (minimal built-in parser, ~50 LOC)
- Locking: Advisory file locks (proven in mulch for multi-agent)
Directory Structure
seeds/
package.json
tsconfig.json
biome.json
CLAUDE.md
CHANGELOG.md
README.md
.claude/
commands/
release.md # /release slash command
.github/
workflows/
ci.yml # lint + typecheck + test on push/PR
publish.yml # CI publish: auto-tag + GitHub release + npm publish
scripts/
version-bump.ts # Bump version in package.json + src/version.ts
src/
index.ts # CLI entry + command router
version.ts # VERSION constant (importable without CLI side-effects)
types.ts # Issue, Template, Config, constants
store.ts # JSONL read/write/lock/atomic
id.ts # ID generation
config.ts # YAML config load/save
config-schema.ts # JSON Schema for .seeds/config.yaml (sd config schema)
output.ts # JSON + human output helpers
yaml.ts # Minimal YAML parser (flat key-value only)
markers.ts # Marker-delimited section helpers (onboard)
filter.ts # Shared issue filter logic (list + ready)
commands/
init.ts # sd init
create.ts # sd create
show.ts # sd show
list.ts # sd list
ready.ts # sd ready
search.ts # sd search
update.ts # sd update
close.ts # sd close
dep.ts # sd dep add/remove/list
block.ts # sd block
unblock.ts # sd unblock
label.ts # sd label add/remove/list/list-all
sync.ts # sd sync
blocked.ts # sd blocked
stats.ts # sd stats
tpl.ts # sd tpl create/step/list/show/pour/status
migrate.ts # sd migrate-from-beads
doctor.ts # sd doctor
prime.ts # sd prime
onboard.ts # sd onboard
upgrade.ts # sd upgrade
completions.ts # sd completions
config.ts # sd config schema/show/set/unset
test-harness.ts # In-process test harness (captures stdout/stderr/exitCode)
test-harness.test.ts # Test harness self-tests
cli-smoke.test.ts # CLI binary smoke tests (real subprocess)
markers.test.ts # Marker section tests
store.test.ts # Core data layer tests
id.test.ts # ID generation tests
yaml.test.ts # YAML parser tests
commands/
init.test.ts
create.test.ts
dep.test.ts
tpl.test.ts
doctor.test.ts
prime.test.ts
onboard.test.ts
completions.test.ts
label.test.ts
unblock.test.ts
sync.test.ts
config.test.ts
suggestions.test.ts # Typo suggestion tests
timing.test.ts # --timing flag tests
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.
- 5d ago First seen · 492 lines · 5,672 tokens per session scan A 1e1fdac68032
seeds CLAUDE.md is an instructions file published in the GitHub repository jayminwest/seeds (132 stars, last pushed 2d ago), licensed MIT. It adds 5,672 tokens to every session, about $0.0284 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
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.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.