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/aancw/sanban/agents-mdgit clone --depth 1 https://github.com/aancw/sanbanWrote 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/aancw/sanban/agents-md)<a href="https://agentmods.dev/instructions/aancw/sanban/agents-md"><img src="https://agentmods.dev/badge/instructions/aancw/sanban/agents-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 | $0.01583 | $0.01583 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
sanban AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:8900/api/boards \ How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidance for AI Agents
Project
sanban is a general-purpose kanban board with REST API + MCP server. JSON file storage, no database. Designed for solo devs and AI agents.
File Map
| Task | File |
|---|---|
| Storage/CRUD | sanban/storage.py |
| REST API | sanban/rest.py (FastAPI) |
| MCP tools | sanban/mcp_server.py (FastMCP, stdio) |
| Entry point | sanban/server.py |
| Frontend | sanban/static/index.html |
| Board data | ~/.sanban/boards/<id>.json |
| JSON schema | schema.json |
| Package config | pyproject.toml |
API Base
http://localhost:8900/api
Common Tasks
Create a board
curl -X POST http://localhost:8900/api/boards \
-H 'Content-Type: application/json' \
-d '{"name":"my-board"}'
Optional: pass columns to customize column names.
curl -X POST http://localhost:8900/api/boards \
-H 'Content-Type: application/json' \
-d '{"name":"my-board","columns":["todo","doing","done"]}'
List boards
curl http://localhost:8900/api/boards
Get a board with items
curl http://localhost:8900/api/boards/<board_id>
Delete a board
curl -X DELETE http://localhost:8900/api/boards/<board_id>
Rename a board
curl -X PATCH http://localhost:8900/api/boards/<board_id> \
-H 'Content-Type: application/json' \
-d '{"name":"new-name"}'
Add an item
curl -X POST http://localhost:8900/api/boards/<board_id>/items \
-H 'Content-Type: application/json' \
-d '{"title":"Fix bug","priority":"high","effort":"S"}'
List items (with filters)
curl 'http://localhost:8900/api/boards/<board_id>/items?status=in_progress&q=bug&tag=urgent&assignee=alice'
Get a single item
curl http://localhost:8900/api/boards/<board_id>/items/<item_id>
Move an item
curl -X PATCH http://localhost:8900/api/boards/<board_id>/items/<item_id> \
-H 'Content-Type: application/json' \
-d '{"status":"done"}'
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.
- 3d ago First seen · 189 lines · 1,583 tokens per session scan A 13c0ff6d5ce6
sanban AGENTS.md is an instructions file published in the GitHub repository aancw/sanban (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,583 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
collattice CLAUDE.md
Instructions for MrBildo/collattice, covering collattice, repository rules — hard, tech stack, build & run and prerequisites.
kagan AGENTS.md
Instructions for kagan-sh/kagan, covering agents.md, commands, build and package, code map and architecture constraints.
claudine AGENTS.md
Instructions for salam/claudine, covering atomic commits, specs, issue and bug reporting and fixing, implementation and misc.
claudine CLAUDE.md
Instructions for salam/claudine, a project described as: A kanban board for managing Claude Code conversations.
kaneo CLAUDE.md
Claude Code instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
kanban CLAUDE.md
Claude Code instructions for kanban-rs/kanban, covering claude.md, project overview, architecture philosophy, solid principles applied and workspace structure.