culi CLAUDE.md

culi CLAUDE.md is an instructions file for coding agents from hung12ct/culi. It costs 1,208 tokens per session, scanned A, original, MIT.

Project instructions for Culi, a tool that selects relevant notes and guidance for coding-agent requests. It stores these notes as small cards and can learn from conversations and Git history.

In plain words
What is it for?
Building, running, and maintaining Culi, including its Go code, knowledge store, search index, hooks, and MCP server.
Why use it?
It reduces repeated project instructions and avoids loading unrelated guidance into every request.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/hung12ct/culi/claude-md
Clone the repo
git clone --depth 1 https://github.com/hung12ct/culi

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.

agentmods badge for culi CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hung12ct/culi/claude-md.svg)](https://agentmods.dev/instructions/hung12ct/culi/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hung12ct/culi/claude-md"><img src="https://agentmods.dev/badge/instructions/hung12ct/culi/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,208 This file is loaded in full into every session.
When invoked 1,208 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01208 $0.01208
Opus 5 $0.00604 $0.00604
Sonnet 5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 4d ago against content hash d588020cf6bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

culi 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 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Culi

Culi (cà phê culi — the single dense peaberry bean; sibling of Phin) is a context orchestrator for Claude Code and OpenAI Codex: one canonical knowledge store of small "cards" (rules / skills / lessons / styles / patterns), token-budgeted context injection via harness hooks, on-demand depth via an MCP server, and background learning from transcripts + git history. Built on gopheragent. Pure Go, one binary, no CGO.

Product goal: kill per-repo CLAUDE.md/skill duplication and inject only the most relevant context per prompt — small, dense, concentrated. Like the bean.

Full approved design: ~/.claude/plans/right-now-for-every-zazzy-graham.md (retrieval funnel, schemas, learning pipelines, phased roadmap).

Architecture

  • One binary culi, subcommand dispatch in cmd/culi/main.go (stdlib flag, no cobra).
  • Files are truth: ~/.culi/knowledge/ (git-init'd markdown cards with YAML frontmatter) is the source of truth for cards; ~/.culi/index.db provides SQLite FTS5 BM25 + embeddings and also holds runtime activity. Card-search tables are rebuildable, while explicit forward migrations preserve injections, card stats, session state, and metadata across schema changes.
  • Push: culi hook <event> — normalized Claude/Codex UserPromptSubmit, SessionStart, Stop, and SessionEnd adapters.
  • Pull: culi mcp — stdio MCP server (modelcontextprotocol/go-sdk): search_context, expand_card, save_lesson.
  • Learning (internal/learn/): Claude/Codex transcript mining, style synthesis, branch→CLAUDE.md/AGENTS.md generation, cross-branch patterns — OpenAI/Anthropic API, Codex/Claude terminal, or Ollama backends behind hard daily caps. Codex lifecycle workers also perform a throttled read-only rollout scan as a missing-transcript_path fallback; scanner telemetry is content-free and surfaced by culi doctor.
  • Embeddings: local Ollama (nomic-embed-text) behind gopheragent's tools.Embedder; every path degrades gracefully to BM25-only when Ollama is down.
  • Review console: culi serve — local net/http server (internal/serve/) serving an embedded vanilla-JS dashboard (embed.FS, no build step): overview, candidate review, knowledge base + search, injection activity (per-event card breakdown + repo attribution), settings/repos manager. Off the hot path, so stdlib-only (C2) does not apply. Read-mostly; card actions (down/retire/ remove/edit) and config/repos writes are git-backed and respect C4 (retire = reversible status flip; hand-authored cards never round-trip through Render).

Read the full file on GitHub · 71 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.

  1. 4d ago First seen · 71 lines · 1,208 tokens per session scan A d588020cf6bd

Subscribe to this mod's changes

culi CLAUDE.md is an instructions file published in the GitHub repository hung12ct/culi (2 stars, last pushed 5d ago), licensed MIT. It adds 1,208 tokens to every session, about $0.0060 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.