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 skills/romiluz13/auto-pi/bearingsnpx 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.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 | $0.00084 | $0.00590 |
| Opus 5 | $0.00042 | $0.00295 |
| Sonnet 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 4d 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.
- 4d 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 18d ago), licensed MIT. It adds 84 tokens to every session and 590 once invoked, about $0.0004 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 skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
teach
Teach the user a new skill or concept, within this workspace.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.