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 skills add openclaw/nix-openclaw-tools --skill imsggit clone --depth 1 https://github.com/openclaw/nix-openclaw-toolsWrote 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/skills/openclaw/nix-openclaw-tools/imsg)<a href="https://agentmods.dev/skills/openclaw/nix-openclaw-tools/imsg"><img src="https://agentmods.dev/badge/skills/openclaw/nix-openclaw-tools/imsg/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/skills/openclaw/nix-openclaw-tools/imsg"><img src="https://agentmods.dev/badge/skills/openclaw/nix-openclaw-tools/imsg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 105 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 246 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.02733 |
| Opus 5.5 | $0.00015 | $0.01093 |
| Sonnet 5.5 | $0.00007 | $0.00547 |
| Haiku 4.5 | $0.00004 | $0.00273 |
Grade A, and why
imsg 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 2mo 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imsg
Use the generic message tool first for actions that its current iMessage schema exposes. Use imsg when the task needs local Messages.app history, target discovery, watching, or an administrative/private-API capability that is not exposed by message.
Do not use this skill for Telegram, Signal, WhatsApp, Discord, Slack, or for replying inside the current OpenClaw conversation when the configured channel already routes the reply.
Agent Flow
- Resolve the conversation first.
- Choose DM, existing group, or new group.
- Prefer an available
messageaction; otherwise pick the lowest-capabilityimsgcommand that preserves the requested semantics. - Confirm any send or visible state change unless the user already gave exact recipient, content, and action.
- Execute with stable identifiers: prefer
--chat-idfor normal sends/watch/history and--chatchat GUID for bridge actions.
Never infer a recipient from a casual name alone when several chats or handles could match. Show the matched display name, handle(s), group participants, and message text/action before sending.
Host Requirements
- macOS 14+ with Messages.app signed in for send/react/bridge actions.
- Private API mode is strongly encouraged for OpenClaw iMessage. It unlocks replies, precise tapbacks, effects, polls, attachment replies, read/typing actions, and group management. Basic mode is a fallback for reads plus plain text/file send.
- Full Disk Access for the process context that runs
imsgor OpenClaw; reads fail without Messages DB access. - Automation permission for Messages.app when using public
send. - Accessibility permission for the process context that runs public
imsg react; it uses System Events UI automation. Bridgetapbackuses private API instead. - Optional Contacts permission for contact-name resolution.
- SMS sends require Text Message Forwarding from the user's iPhone to this Mac.
- Linux reads a copied
chat.dbonly; it cannot send, react, launch Messages.app, mark read, or type.
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.
- 2mo ago Changed · +1 lines 34c4d895d855
- 2mo ago First seen · 250 lines · 37 tokens per session scan A ab9ec1885a75
imsg is a skill published in the GitHub repository openclaw/nix-openclaw-tools (54 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 2,733 once invoked, about $0.0001 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 2026-08-30.
imsg compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| imsgopenclaw/nix-openclaw-tools | Skill | 54 | 3d ago | MIT | A | 37 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |