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/seemethere/spool/agents-mdgit clone --depth 1 https://github.com/seemethere/spoolWhat 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 | $0.01702 | $0.01702 |
| Opus 5 | $0.00851 | $0.00851 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
spool 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spool Agent Instructions
Always read first
CONTEXT.md— canonical domain language and relationships.ROADMAP.md— current implementation sequence, with Dogfooding Readiness first.- Relevant
docs/adr/*.mdfiles before changing architecture, workflow, persistence, delivery, or launcher behavior.
Use the terms from CONTEXT.md exactly. Avoid Linear/GitHub/PR-shaped language unless discussing future optional integrations.
Product direction
Spool is a local-first task backend for speeding up agent-driven development. The first priority is Dogfooding Readiness: Spool should become useful enough to build Spool with Spool as quickly as possible.
Keep v1 focused on:
- Spool Service + Spool API
- Task Queues
- Tasks, Task States, requirements, Workpad Notes
- Agent Runs and Claim Leases
- Local Worktree Delivery
- Pi Launcher using
pi --mode rpc - Minimal Spool Pi Extension
- CLI-first observability
Do not expand v1 into:
- A Linear clone or generic project management system
- A GitHub/PR-dependent workflow
- A web UI/dashboard
- Multi-tenant permissions/ACLs
- Import/sync from external trackers
- Custom workflows beyond the fixed v1 Task State lifecycle
Implementation stack
Core Spool implementation:
- Rust
axumfor HTTPsqlx+ SQLite for persistence/migrationsclapfor CLItokiofor async process/server workserdefor API typestracingfor logsuuidfor internal IDstimefor timestamps
Pi integration:
- TypeScript Spool Pi Extension
- Communicate with Spool through the HTTP API
- Do not share in-process code between Rust Spool and the extension
Dogfooding Readiness path
Prioritize these milestones in order:
- Rust skeleton, config/init/migrations, health/version.
- Queues, Tasks, requirements, Workpad Notes, Audit Events, bootstrap creation, show/status CLI.
- Claim/lease/run lifecycle and fake launcher worker loop.
- Local Worktree Delivery setup, Pi Launcher RPC, minimal Spool Pi Extension.
- Run transcripts/session data, status/run show, manual dogfood merge or first Integrating implementation, deterministic 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.
- 2d ago First seen · 163 lines · 1,702 tokens per session scan A 336c4b4abdc2
spool AGENTS.md is an instructions file published in the GitHub repository seemethere/spool (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,702 tokens to every session, about $0.0085 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
anarlog AGENTS.md
Instructions for fastrepl/anarlog, covering commands, pre-commit verification, guidelines, code style and cli tui command architecture.
shodh-memory CLAUDE.md
Instructions for varun29ankuS/shodh-memory, covering shodh-memory project instructions, must rules, code standards, persistent memory (shodh-memory mcp) and codebase map.
Recall AGENTS.md
Instructions for samzong/Recall, covering agents.md, commands, architecture and boundaries.
ZhiWei CLAUDE.md
Instructions for ntygod/ZhiWei, covering claude.md, project overview, build & development commands, backend and frontend.
codemark GEMINI.md
Instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.