What is logbook AGENTS.md?

Repository instructions for Logbook, a small command-line tool and MCP wrapper for recording and querying agent notes.

Use them when changing Logbook's detector, cache, event ledger, command-line interface, MCP server, or release process.

They document tests and release rules that protect event detection, cache behavior, versioning, and consistent JSON output.

How promptwheel-ai/logbook configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to promptwheel-ai/logbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/promptwheel-ai/logbook/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/promptwheel-ai/logbook

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/promptwheel-ai/logbook/agents-md/github.svg)](https://agentmods.dev/instructions/promptwheel-ai/logbook/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/promptwheel-ai/logbook/agents-md"><img src="https://agentmods.dev/badge/instructions/promptwheel-ai/logbook/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/promptwheel-ai/logbook/agents-md"><img src="https://agentmods.dev/badge/instructions/promptwheel-ai/logbook/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 908 This file is loaded in full into every session.

When invoked 908 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00908	$0.00908
Opus 5.5	$0.00363	$0.00363
Sonnet 5.5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured 2mo ago against content hash bd9c59f1a900, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

logbook 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 2mo 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.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

logbook — agent notes

Single-file zero-dep CLI (bin/logbook.mjs) + MCP wrapper (mcp/server.mjs). Run tests: npm test (root) and cd mcp && npm test (behavioral, drives the real server over stdio). Inside this repo use node bin/logbook.mjs, not npx — npm prefers the same-name local package and shadows the registry.

Release invariants (regression-tested — keep all of them green)

A fresh self-run on THIS repo reports 0 suppression events. The detector must never flag its own regex tables or comments about skip APIs (diff +/- prefix is stripped before isMention; call-syntax idioms inside comments are prose).
Bump EXTRACTOR_VERSION whenever detector precision changes — the events.jsonl cache is rejected on mismatch, so old ledgers can't mask a fix. Verify fresh and upgraded-cache self-runs agree.
Public JSON is cache-invariant: --json (and MCP logbook_query) byte-identical with and without LOGBOOK_NO_CACHE=1. Events are stamped with xv at birth in collectEvents, not at write time.
Cache freshness is the exact current ordered non-merge Git window, never “newest cached SHA is present.” Merges can introduce older-dated side commits; reuse rows by immutable full SHA, scan missing SHAs, then restore Git's canonical order.
init writes the ordered read → bounded path-context → verify workflow with neutral --by MODEL attribution and creates the CLAUDE.md @AGENTS.md bridge; exact released blocks migrate, user-edited blocks are never touched.
DEFAULT_MAX is the single source for the commit window — the ledger cache gate in loadEvents depends on it.
Never turn "unmeasurable" into clean: a failed diff scan sets A.degraded (surfaced in LOGBOOK.md); a failed git grep in audit throws instead of reporting clean.
All repository-controlled Markdown and agent-facing audit values go through the single sanitizeContextText implementation. Rendering must never mutate events.jsonl, --json, or query output.
Generated artifacts use atomic per-file replacement and one shared stamped record. logbook doctor is read-only and must fail stale/tampered bundles or shadowing wiring without repairing them while it checks.

Read the full file on GitHub · 69 lines

Changes

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.

2mo ago First seen · 69 lines · 908 tokens per session scan A bd9c59f1a900

Subscribe to this mod's changes

logbook AGENTS.md is an instructions file published in the GitHub repository promptwheel-ai/logbook (3 stars, last pushed 3mo ago), licensed MIT. It adds 908 tokens to every session, about $0.0036 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.

Building agents Claude Code Memory and context ai-agents codex developer-tools git-history mcp

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

logbook: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

logbook — agent notes

Release invariants (regression-tested — keep all of them green)

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deepseek-harness AGENTS.md