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 promptwheel-ai/logbook --skill plugingit clone --depth 1 https://github.com/promptwheel-ai/logbookWrote 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/promptwheel-ai/logbook/plugin)<a href="https://agentmods.dev/skills/promptwheel-ai/logbook/plugin"><img src="https://agentmods.dev/badge/skills/promptwheel-ai/logbook/plugin/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/promptwheel-ai/logbook/plugin"><img src="https://agentmods.dev/badge/skills/promptwheel-ai/logbook/plugin.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 | $0.00078 | $0.01184 |
| Opus 5.5 | $0.00031 | $0.00474 |
| Sonnet 5.5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
logbook 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logbook
npx @promptwheel/logbook # analyze current repo → 3 files
npx @promptwheel/logbook journey # the story, in color (writes nothing)
npx @promptwheel/logbook doctor # read-only artifact/wiring/query health
npx @promptwheel/logbook --json # events to stdout (writes nothing)
Never touches source or git history; writes only its own brief files. -n N caps commits; --since/--until for era scoping.
After running:
- Read
$(git rev-parse --show-toplevel)/LOGBOOK.mdcompletely before any history query. Do not replace this step with a broad keyword search. - Relay "What a fresh session should know" plus the 2-3 most notable findings. If Historical signal is LOW, use it only as a hotspot map; otherwise inspect task-relevant do-not-retry entries and fragile areas.
- TRIAGE, don't parrot: the logbook is the recall layer; you are the precision
layer. Cross-reference leads against the current task and verify any claim
you act on with
git show <sha>. Confirm it still applies at HEAD.
Findings are leads, not verdicts — a suppression event means "a human should
look here," not misconduct. If the repo is shallow, offer
git fetch --unshallow first.
If the artifacts, wiring, or query path look stale or inconsistent, run
npx -y @promptwheel/logbook@latest doctor and report its compact output.
Doctor is diagnostic and read-only; do not treat it as a refresh.
Investigation mode (when the user asks to dig into findings)
For each Notable event or flagged lead worth pursuing: git show <sha> the
commit, read the actual diff, and classify it — real weakening / sanctioned
maintenance / classifier artifact — with one line of evidence each. Check
whether flagged suppressions are STILL in the current tree (grep HEAD for
the skip/ignore near the flagged location). Present the triage as YOUR
judgment layered on the deterministic record — never edit the logbook files
to match your conclusions; the record and the reading stay separate.
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 · 102 lines · 78 tokens per session scan A 507165fe765c
logbook is a skill published in the GitHub repository promptwheel-ai/logbook (3 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,184 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 2026-08-31.
Other skills, from other repositories
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
git-ai-search
Search and restore AI conversation context from git history.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
recall-rationale
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.