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 skills add romiluz13/auto-pi --skill bearingsgit clone --depth 1 https://github.com/romiluz13/auto-piWrote 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/skills/romiluz13/auto-pi/bearings)<a href="https://agentmods.dev/skills/romiluz13/auto-pi/bearings"><img src="https://agentmods.dev/badge/skills/romiluz13/auto-pi/bearings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/romiluz13/auto-pi/bearings"><img src="https://agentmods.dev/badge/skills/romiluz13/auto-pi/bearings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.00590 |
| Opus 5.5 | $0.00034 | $0.00236 |
| Sonnet 5.5 | $0.00017 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
bearings 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bearings
Generate a complete standalone snapshot from all active Pi sessions, so you can resume in one read after a break, a night, or a context reset.
Inspired by FirstMate's bearings skill (kunchenguid/firstmate), adapted for auto-pi's multi-session architecture. Zero dependencies — reads local state files only.
What it does
-
Gather live session state. Read
~/.pi/agent/session-status.jsonl— each line is a JSON object written by the status extension on everyagent_start/agent_end:{"sessionId":"abc","project":"/path","phase":"build","task":"add pagination","status":"working","ts":"2026-07-20T..."}Also read
~/.pi/agent/decisions.jsonfor open decisions. -
Compose the 4-section digest. Every section ALWAYS renders, even when empty:
- Your Call — decisions that need your action now. Open items from
decisions.jsonthat are unresolved. Empty-state: "Nothing needs your action right now." - Recently Landed — completed work since last bearings. Check
git log --oneline -5in each project with active state. Empty-state: "No recent completions." - Underway — live sessions currently working. One line per session: project, phase, task, status. Empty-state: "Nothing is underway."
- Charted Next — check open issues for what to tackle next. Empty-state: "Nothing is queued."
- Your Call — decisions that need your action now. Open items from
-
Write the dated report to
~/.pi/agent/bearings/<YYYY-MM-DD>.mdand surface the concise digest in chat.
Rules
- Read-only. Never mutates session state, decisions, or workflow state as a side effect.
- Every section always renders with its empty-state sentence.
- Every report is a complete current snapshot, never a delta against a prior report.
- The 4 buckets are mutually exclusive: needs-your-action = Your Call, done = Recently Landed, self-progressing = Underway, not-yet-started = Charted Next.
- If state suggests an action (PR ready, gate arrived), name it in its section and let the user decide — do not take the action from inside this skill.
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.
- 1mo ago First seen · 39 lines · 84 tokens per session scan A c6442e0cff8a
bearings is a skill published in the GitHub repository romiluz13/auto-pi (10 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 590 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
configure-pi-starship
Configure @narumitw/pi-starship and answer questions about its pi-starship.toml settings. Use when the user asks to create, edit, repair, migrate, or understand pi-starship.toml, or asks which pi-starship module, variable, option, style, palette, preset, or runtime behavior to use. Do not use for generic TOML, shell…
configure-pi-sync
Explain @narumitw/pi-sync settings and guide safe setup through its existing manager. Use when the user asks how to configure pi-sync.json, choose Git, WebDAV, R2, or S3 storage, select synced content, understand automatic controls, or recover unsupported settings. This skill provides guidance only, not settings edits…
fabric-foreman
Starts a bounded Jev foreman above Main's coding work, assessing progress, drift, blockers, and verification per turn or at agent settlement with deterministic intervention policy.
write-swift
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…