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 adbertram/cli-tools --skill muse-chat-cligit clone --depth 1 https://github.com/adbertram/cli-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/adbertram/cli-tools/muse-chat-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/muse-chat-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/muse-chat-cli/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/adbertram/cli-tools/muse-chat-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/muse-chat-cli.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.01017 |
| Opus 5.5 | $0.00028 | $0.00407 |
| Sonnet 5.5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
muse-chat-cli 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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<project_overrides> Before acting on this skill, run:
~/.agents/skills/skill-expert/scripts/load-skill-overrides.sh muse-chat-cli
Apply any printed instructions alongside this skill's own workflow: they extend it and never repeal its limits. No output means no project override is in effect. A non-zero exit means the project's override file is broken -- report it and stop rather than silently running unmodified. </project_overrides>
<quick_start> The CLI follows this pattern:
muse-chat <command-group> <action> [arguments] [options]
| Task | Command |
|---|---|
| Sign in with the persistent browser profile | muse-chat auth login |
| Check live authentication | muse-chat auth status |
| Send to the main chat and return immediately | muse-chat chat send <MESSAGE> |
| Send to a specific side chat | muse-chat chat send <MESSAGE> --chat-id <UUID> |
| Send and wait for the final reply | muse-chat chat send <MESSAGE> --monitor --timeout <SECONDS> |
| Resume monitoring the latest turn | muse-chat chat monitor <CHAT_ID> --timeout <SECONDS> |
| Create a side chat and return immediately | muse-chat side create <MESSAGE> |
| Create a side chat and wait for the reply | muse-chat side create <MESSAGE> --monitor --timeout <SECONDS> |
| List durable chat IDs | muse-chat chat list |
| Read chat history | muse-chat chat get <CHAT_ID> |
| </quick_start> |
<essential_principles>
MANDATORY: Consult the adjacent usage.json before executing any
muse-chat command. It is the canonical command map for arguments, options,
defaults, and nested command paths. Never guess command syntax.
<reference_index>
usage.json -- Complete generated command tree, arguments, options, and defaults.
muse-chat --help and subcommand --help -- Live installed command surface.
README.md -- Authentication, response contracts, and examples.
</reference_index>
<success_criteria>
- The exact requested main or side chat is used.
- Send-only commands return a confirmed submission record.
- Monitored commands return the final reply, a structured timeout, or an approval gate.
- Durable chat IDs are preserved so monitoring can resume without resending. </success_criteria>
<response_correlation>
Completed monitor output combines ordered assistant components with the same
durable turn ID, including prose and cards. Different turn IDs remain an error.
Completion requires one second of unchanged idle content within the overall
timeout; new text/components or activity reset settling. chat get is a
snapshot, with bounded idle hydration settling (up to five seconds), and may
show an active partial response. Use monitor for final replies.
Only newly created side chats can reconcile a temporary submitted-message ID: a bounded empty-history gap is tolerated, then the unique saved user turn must exactly match normalized submitted text. Existing chats never reanchor by text, and reconciliation never resends the message. </response_correlation>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 104 lines · 71 tokens per session scan A d607506c9baf
muse-chat-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,017 once invoked, about $0.0003 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 2026-11-07.
muse-chat-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| muse-chat-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 71 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| open-sourcebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 137 | Claude Code |
| opencli-usagejackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 31 | Claude Code |
| apple-remindersAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 31 | Claude Code, Codex |
| obsidianAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 20 | Claude Code, Codex |
| ffmpegAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 47 | Claude Code, Codex |