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/hainanzhao/clawless/gemini-mdgit clone --depth 1 https://github.com/HainanZhao/ClawlessWrote 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/hainanzhao/clawless/gemini-md)<a href="https://agentmods.dev/instructions/hainanzhao/clawless/gemini-md"><img src="https://agentmods.dev/badge/instructions/hainanzhao/clawless/gemini-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 | $0.00597 | $0.00597 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
Clawless GEMINI.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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Context for Clawless
Bridge connecting local AI agent CLIs (Gemini CLI, OpenCode, Claude Code) to Telegram/Slack via ACP.
Core: BYO-agent — swap CLI runtimes without rebuilding bot integration.
Supported Agents
| Agent | CLI Command | Config Value |
|---|---|---|
| Gemini CLI | gemini |
gemini (default) |
| OpenCode | opencode |
opencode |
| Claude Code | claude |
claude |
Architecture
Messaging (Telegram/Slack) → Clawless Bridge → Agent CLI (ACP)
↓
Scheduler + Callback API
Components: messaging/ (clients), acp/ (session mgmt), core/agents/ (CLI interface), scheduler/ (cron jobs), utils/ (memory/history)
Async Mode
- QUICK: Simple questions, answered immediately
- ASYNC: Tasks needing tools or >10s — returns confirmation, executes in background
Development
npm run dev # Watch mode
npm run build # lint + format + compile
npm run test # vitest
Stack: TypeScript (ESM), Node.js 18+, Biome, Vitest, Pino logging, Zod validation
Config & Persistence
All in ~/.clawless/: config.json, MEMORY.md, conversation-history.jsonl, conversation-semantic-memory.db, schedules.json
API Endpoints (port 8788)
| Endpoint | Purpose |
|---|---|
GET /health |
Health check |
POST /callback/:platform |
Proactive notifications |
POST /api/message |
Send to bound chat |
GET/POST/PATCH/DELETE /api/schedule |
Cron job management |
POST /api/memory/semantic-recall |
Semantic memory retrieval |
Key Files
| Area | Files |
|---|---|
| Entry | index.ts, bin/cli.ts |
| App | app/ClawlessApp.ts, app/AgentManager.ts |
| Agents | core/agents/*.ts |
| ACP | acp/runtimeManager.ts, acp/tempAcpRunner.ts |
| Messaging | messaging/telegramClient.ts, messaging/slackClient.ts, messaging/ModeDetector.ts |
| Scheduler | scheduler/*.ts |
| Utils | utils/config.ts, utils/memory.ts, utils/semanticConversationMemory.ts |
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.
- 5d ago First seen · 69 lines · 597 tokens per session scan A 7e044ce38d84
Clawless GEMINI.md is an instructions file published in the GitHub repository HainanZhao/Clawless (19 stars, last pushed 4mo ago), licensed MIT. It adds 597 tokens to every session, about $0.0030 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 2026-08-30.
Other instructions, from other repositories
EchoBird AGENTS.md
AGENTS.md instructions for edison7009/EchoBird, covering agents.md — echobird, project shape, ci gates (must pass locally before pushing), lesson (learned the hard way) and verification habits.
hapi AGENTS.md
AGENTS.md instructions for tiann/hapi, covering agents.md, what is hapi?, repo layout, architecture overview and reference docs.
open-vibe-island AGENTS.md
AGENTS.md instructions for Octane0411/open-vibe-island, covering agents, goal, required workflow, commit policy and safety rules.
open-vibe-island CLAUDE.md
Claude Code instructions for Octane0411/open-vibe-island, covering claude.md, project, architecture, build & run and dev app (open island dev.app).
sessionview AGENTS.md
AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
wingman AGENTS.md
Instructions for eat-pray-ai/wingman, covering agents.md — wingman (@eat-pray-ai/wingman), quick reference and documentation index.