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/memodb-io/cueclaw/claude-mdgit clone --depth 1 https://github.com/memodb-io/cueclawWrote 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/memodb-io/cueclaw/claude-md)<a href="https://agentmods.dev/instructions/memodb-io/cueclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/memodb-io/cueclaw/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 5.1 | $0.01704 | $0.01704 |
| Opus 5 | $0.00852 | $0.00852 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
cueclaw 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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CueClaw
Orchestrate agent workflows with natural language. Uses the Claude Agent SDK to generate execution plans, confirm with users, and run workflows in the background.
Project Status
MVP implemented (Phases 0-6) with multi-turn planner, decomposed TUI (context/hook architecture), daemon bridge with PID file management, and channel-aware planner. ~316 tests across 33 test files.
Key Concepts
- Workflow: Natural language → Planner (LLM) → PlannerOutput → framework fills id/phase/timestamps → Workflow JSON (DAG of steps)
- Planner Session: Multi-turn conversation with the planner — clarify requirements, store credentials, then generate workflow
- Executor: Parallel DAG execution — independent steps run concurrently via
Promise.all - Channel: Unified interface for TUI, WhatsApp, Telegram —
sendMessagereturns message ID, optionaleditMessagefor in-place status updates - ChannelContext: Identifies channel + sender, threaded through planner for channel-aware system prompt (bot vs TUI)
- Daemon Bridge: Abstraction between TUI and backend — detects external daemon via PID file (
~/.cueclaw/daemon.pid) or system service - TUI Architecture: Decomposed into providers (ThemeProvider → KeypressProvider → DialogManager → AppProvider → AppLayout), context layer (UIStateContext + UIActionsContext), custom hooks (6 in
tui/hooks/), command registry (tui/commands/), theme system (tui/theme/with 3 built-in themes), per-type message components (tui/messages/) - Input References:
$steps.{id}.output(step results) and$trigger_data(trigger payload), resolved at execution time - Container Execution: Opt-in via
container.enabled: truein config.yaml — dev mode usescueclaw-agent:latest(local build viacontainer/build.sh), production uses version-pinnedghcr.io/memodb-io/cueclaw-agent:{version}with auto-pull from GHCR; falls back to local execution if Docker is unavailable or pull fails - Session: Per-step (not per-run) — steps don't share session context to avoid pollution
- File Logging:
initLogger()writes to~/.cueclaw/logs/daemon.log(all processes) andexecutions/subdir (per-workflow); composes with TUI in-memory stream via pino multistream
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.
- 6d ago First seen · 107 lines · 1,704 tokens per session scan A 6d19f5d01c1b
cueclaw CLAUDE.md is an instructions file published in the GitHub repository memodb-io/cueclaw (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,704 tokens to every session, about $0.0085 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
draftly-wps CLAUDE.md
Claude Code instructions for Antares422/draftly-wps, covering claude.md, 项目是什么, 硬性规则, 部署流程 and 架构.
ai-agents security.instructions.md
Instructions for rjmurillo/ai-agents, covering security file rules, must, should, must not and references.
Cerebro AGENTS.md
Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.
discoclaw CLAUDE.md
Instructions for DiscoClaw/discoclaw, covering discoclaw, safety, context loading (strict), identity and workspace file ownership.
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.
coworker CLAUDE.md
Instructions for Array-Ventures/coworker: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.