Borrowing it
Nothing to install: this file belongs to Gunnarguy/PlaudBlender. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Gunnarguy/PlaudBlender/main/CLAUDE.mdgit clone --depth 1 https://github.com/Gunnarguy/PlaudBlenderWrote 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/gunnarguy/plaudblender/claude-md)<a href="https://agentmods.dev/instructions/gunnarguy/plaudblender/claude-md"><img src="https://agentmods.dev/badge/instructions/gunnarguy/plaudblender/claude-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.
<a href="https://agentmods.dev/instructions/gunnarguy/plaudblender/claude-md"><img src="https://agentmods.dev/badge/instructions/gunnarguy/plaudblender/claude-md.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 | $0.01161 | $0.01161 |
| Opus 5.5 | $0.00464 | $0.00464 |
| Sonnet 5.5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
PlaudBlender CLAUDE.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 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlaudBlender - Chronos: Plaud recordings to a searchable timeline (Python Dash, SQLite, Qdrant) plus the PlaudBlenderiOS Swift client
Verify
Before any commit (copilot-instructions.md, Coding Rules 5):
.venv/bin/python -m pytest tests/ # 419 test functions in 44 files; 422 passed on 2026-08-29 (HANDOFF.md); fits a 2 min Bash timeout, once exceeded it (brief section 11)
For one change, run the matching file first: .venv/bin/python -m pytest tests/test_<module>.py.
Do not report done until this exits 0 and you have read the output.
The suite stays off the real database since commit c3af69b; five full runs leave data/brain.db byte-identical (HANDOFF.md).
Production check after a deploy: on the Pi (SSH alias in HANDOFF.md) run deploy/verify-pi.sh, which prints PASS, WARN or FAIL
per service, and confirm /api/v1/health answers. Diagnose from the Pi, never from the Mac.
Never
- Never push to
mainunless Gunnar asked for a deploy in this session. The Pi pullsorigin/mainevery 10 minutes (deploy/systemd/chronos-auto-update.timer,OnUnitActiveSec=10min) with no review gate: push is deploy. Until 2026-08-29 only an auto-memory note encoded this (brief section 12.2). - Never diagnose production from the Mac's
data/brain.db. It is a dev copy; the Mac.envhas no Plaud credentials and cannot ingest. Real data is the Pi's~/PlaudBlender/data/brain.db(HANDOFF.md, Gotchas). - Never rewrite a Plaud device API client. The REST device endpoints 404 for this account and the official MCP has no device tool;
plaud_device.py(562 lines) was deleted for that reason in76f6070(HANDOFF.md). - Never make a billable model call without
track_usage()fromsrc.chronos.cost_tracker, and never scatterload_dotenv(); secrets arrive throughsrc/config.py(copilot-instructions.md, Coding Rules 1 and 7). - Never run a pattern check under zsh. Unquoted
$VARdoes not word-split and--include=*.pyerrors, and both produced false passes (HANDOFF.md, Gotchas). Usebash -c.
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 · 46 lines · 1,161 tokens per session scan A 12e50095623c
PlaudBlender CLAUDE.md is an instructions file published in the GitHub repository Gunnarguy/PlaudBlender (6 stars, last pushed 23d ago), licensed MIT. It adds 1,161 tokens to every session, about $0.0046 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 2026-09-15.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.