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 instructions/doublegremlin181/potluck/claude-mdgit clone --depth 1 https://github.com/DoubleGremlin181/potluckWrote 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/doublegremlin181/potluck/claude-md)<a href="https://agentmods.dev/instructions/doublegremlin181/potluck/claude-md"><img src="https://agentmods.dev/badge/instructions/doublegremlin181/potluck/claude-md.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 | $0.01275 | $0.01275 |
| Opus 5 | $0.00638 | $0.00638 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
potluck 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Potluck — AI Context
Privacy-first personal knowledge database for your AI. Local-first: SQLite + FTS5, FastAPI + React SPA, MCP-native. v1 is a ground-up rewrite; the master plan (phases, architecture, perf budgets, locked decisions) lives in pinned GitHub issue #98 — update it as phases close.
Architecture
src/potluck/
core/ config (pydantic-settings), paths (platformdirs), errors
models/ Pydantic DTOs only — NO ORM
storage/ SQLite: pragmas, single writer thread, NNN_*.sql migrations (PRAGMA user_version)
ingest/ streaming ETL plane: readers, sources/<name>/, content-hash ledger (P1+)
enrich/ derived-data reconciler plane: anti-join work discovery, executors (P5+)
search/ FTS5 query builder, VecIndex protocol, hybrid RRF (P1+)
services/ THE shared layer — plain sync functions (ctx, req) -> resp with Pydantic DTOs
api/ mcp/ cli/ thin adapters over services (enforced by import-linter)
testing/ synthetic generators (shipped; reused by tests, fixtures, bench)
bench/ scenario registry, runner, compare
web/ Vite + React + TS + Tailwind + shadcn/ui (dist built in CI, served by FastAPI)
Absolute rules
- Service-layer rule:
api/,mcp/,cli/import onlyservices+models(+coreinfrastructure) — neverstorage/ingest/enrich/searchdirectly. CI enforces this (import-linter contracts inpyproject.toml). - No conditional imports. No optional dependencies / extras — ever. All imports top-of-file. ML dependencies become core dependencies when their phase lands. One install shape for everyone.
- Batch-first: data paths take batches (one
IN(...)dedup query + oneexecutemanyper batch); no per-item DB round-trips. Ingestion stays a single-threaded loop until a bench scenario proves otherwise. - All writes go through
Database.write()(single writer thread owns the sole write connection); reads use the per-thread query-only connections fromDatabase.read(). - Pydantic DTOs at boundaries; mypy strict; avoid
Any. Raise Potluck-specific exceptions fromcore/errors.py, adding each one only with the feature that raises it. - Fixtures are generated:
tests/fixtures/contains onlypotluck.testinggenerator output. The PII guard (scripts/check_fixtures.py) runs in pre-commit + CI. Never commit real export content; consult real exports locally for shape only.
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.
- 2d ago First seen · 82 lines · 1,275 tokens per session scan A dba5a9833623
potluck CLAUDE.md is an instructions file published in the GitHub repository DoubleGremlin181/potluck (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,275 tokens to every session, about $0.0064 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.