Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/rawwerks/ypi/agents-md)<a href="https://agentmods.dev/instructions/rawwerks/ypi/agents-md"><img src="https://agentmods.dev/badge/instructions/rawwerks/ypi/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 5.1 | $0.05026 | $0.05026 |
| Opus 5 | $0.02513 | $0.02513 |
| Sonnet 5 | $0.01005 | $0.01005 |
| Haiku 4.5 | $0.00503 | $0.00503 |
Grade A, and why
ypi AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — ypi
Running Prose Programs & Background Tasks
Launch long-running tasks in tmux with a sentinel file. The notify-done extension
watches /tmp/ypi-signal-* and injects a message into your conversation when
the task finishes — no sleeping, no polling, no tmux capture-pane loops.
How it works:
- Idle →
triggerTurnfires immediately, you get a new turn - Busy (mid-tool-execution) → message is steered in, delivered after the current tool finishes
- Either way, the notification appears in your message history and you respond to it
# Launch with sentinel (you'll be woken up when it finishes)
tmux send-keys -t eval:land "cd ~/Documents/GitHub/ypi && rp ypi .prose/land.prose; echo done > /tmp/ypi-signal-${YPI_INSTANCE_ID}-land" Enter
# That's it. Keep working on other things. You'll get a message like:
# ⚡ Background task "land" completed: done
# ...and a new turn is triggered so you can respond to it.
IMPORTANT: Do NOT poll or sleep-loop waiting for background tasks.
Do not sleep && tmux capture-pane in a loop. Do not check progress unless
asked. Just keep working — the extension will interrupt you when it's ready.
Sentinel naming: /tmp/ypi-signal-${YPI_INSTANCE_ID}-{name} — always include
$YPI_INSTANCE_ID so the signal reaches THIS instance, not a sibling. The {name}
part appears in the notification. File contents become the notification body.
The file is deleted after consumption.
Key programs:
rp ypi .prose/land.prose— "land it" / "land the plane": tests, push, handoffrp ypi .prose/release.prose confirm_release='Approved.'— cut an npm releaserp ypi .prose/check-upstream.prose— verify Pi compatibilityrp ypi .prose/incorporate-insight.prose insight='...'— propagate an insight across the repo
Version Control: Use jj, not git
This repo uses jj (Jujutsu) for version control. Git is only for GitHub sync.
# Working with changes
jj status # What's changed
jj diff # See the diff
jj describe -m "message" # Describe current change
jj new # Start a new change on top
# Pushing to GitHub
jj bookmark set master # Point master at current change
jj git push # Push to GitHub
# Reviewing sub-agent work
jj log # See all changes including sub-agent workspaces
jj diff -r <change-id> # Review a sub-agent's edits
jj squash --from <change-id> # Absorb a sub-agent's work into yours
jj abandon <change-id> # Discard a sub-agent's work
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.
- 6d ago First seen · 381 lines · 5,026 tokens per session scan A 98c76fb42693
ypi AGENTS.md is an instructions file published in the GitHub repository rawwerks/ypi (386 stars, last pushed 2mo ago), licensed MIT. It adds 5,026 tokens to every session, about $0.0251 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
autocontext CLAUDE.md
Claude Code instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.
autocontext AGENTS.md
AGENTS.md instructions for greyhaven-ai/autocontext, covering agent guide, pick the right surface, working directories, setup and parity-last changes.
pi-fabric AGENTS.md
AGENTS.md instructions for monotykamary/pi-fabric, covering agents.md, golden rule: build when done, before committing, incremental checks while iterating and package manager.
atlasclaw AGENTS.md
AGENTS.md instructions for CloudChef/atlasclaw, covering agents.md - atlasclaw coding guidelines, build / test / lint commands, backend (python), run the service and run all tests.
swarmclaw CLAUDE.md
Instructions for swarmclawai/swarmclaw, covering claude.md, keeping instructions in sync, dev server, code quality and architecture.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.