What is muse-commands?

A set of commands for saving, resuming, and ending coding work across sessions. It preserves the selected role, decisions, work lane, and supporting evidence.

Use it to continue a task later, save a checkpoint, or close a work session while keeping its relevant project state.

It prevents context and decisions from being lost when work pauses or moves to another session.

muse-commands — Skill for Claude Code and Codex by myths-labs

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.

Any agent

npx skills add myths-labs/muse --skill muse-commands

Clone the repo

git clone --depth 1 https://github.com/myths-labs/muse

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/myths-labs/muse/muse-commands/github.svg)](https://agentmods.dev/skills/myths-labs/muse/muse-commands)

Your own site

<a href="https://agentmods.dev/skills/myths-labs/muse/muse-commands"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/muse-commands/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/myths-labs/muse/muse-commands"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/muse-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 827 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00827
Opus 5	$0.00020	$0.00413
Sonnet 5	$0.00008	$0.00165
Haiku 4.5	$0.00004	$0.00083

Measured 2d ago against content hash 8bbefcbfe085, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

muse-commands 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 2d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (scripts/muse-cli.py, scripts/muse-closeout.py, scripts/muse-config.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/core/muse-commands/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MUSE continuity commands

Read only the workflow needed for the current action. The installed shared runtime is .agent/skills/muse-commands, its workflows are .agent/workflows, and project configuration is .muse/config.json. Paths in this guide are relative to the installed project; use the absolute resolved script path when the shell cwd differs.

User interaction

The user may say continue, /resume strategy Lane A, /save, or /bye. The agent derives the goal, acceptance checks, constraints and next action from the request, shared role record and relevant checkpoint. Do not require the user to fill a goal/acceptance/constraints form. Do not change role based on cwd, provider or project. A project may have Strategy implement work directly; respect its policy. Do not introduce a Strategy-to-Build handoff unless actually requested.

Keep the same Lane by default. Use a new logical Lane only when independent scope or continuation warrants it within user authorization; changing provider or reaching a context threshold does not create one. A new app task is separate and requires user intent. Do not silently reopen a CLOSED Lane; first read its explicit reopen conditions. A missing checkpoint does not prove an old task is new.

Dispatch

Use bash .agent/skills/muse-commands/scripts/muse-doctor.sh as the helper prefix. It never calls a model or executes product tasks by itself.

On /resume, run parse-resume '<exact command>' '<workspace>' and lock the returned role_home/role/Lane. Run resume-workflow --command '<exact command>' --workspace '<workspace>', then read only the returned daily or legacy workflow.
On ordinary save, read .agent/workflows/save.md; use save-daily, not full Bye.
On explicit Bye, select bye-workflow --command '<locked resume>' --workspace '<workspace>' and follow that workflow. A valid unchanged closeout receipt can be checked; changed requirements/evidence or failing gates must be addressed.
Other commands use resolve /<command> '<workspace>' and the returned workflow.

Read the full file on GitHub · 70 lines

Files

What ships with it

19 files 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.

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.

2d ago First seen · 70 lines · 40 tokens per session scan A 8bbefcbfe085

Subscribe to this mod's changes

muse-commands is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 827 once invoked, about $0.0002 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 2026-09-07.

Productivity Project management ai ai-pair-programming claude context-management cursor developer-tools

handoff

End-of-session workflow to leave durable project context for the next chat. Use whenever the user says "handoff," "wrap up," "end of session," "before we end," "close out this session," "let's wrap," "we're done," "wrap this up," "closing out," "starting a new session," or "before I start fresh." Do NOT use for…

ngreenwall/claude-skills · 111 tokens

muse-commands

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

MUSE continuity commands

User interaction

Dispatch

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

handoff

ctx resume

issue-creation

systemic-issue-triage

weekly

ijfw-workflow