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.
git clone --depth 1 https://github.com/emadd/mise-en-claudeWrote 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/commands/emadd/mise-en-claude/mise-init)<a href="https://agentmods.dev/commands/emadd/mise-en-claude/mise-init"><img src="https://agentmods.dev/badge/commands/emadd/mise-en-claude/mise-init/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/commands/emadd/mise-en-claude/mise-init"><img src="https://agentmods.dev/badge/commands/emadd/mise-en-claude/mise-init.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 | $0.00047 | $0.00640 |
| Opus 5 | $0.00023 | $0.00320 |
| Sonnet 5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
mise-init 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 9d 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.
What it actually says
You are running /mise-init — mise's re-runnable setup / rescue / update entry point: the
installed equivalent of pasting PROMPT.md. mise is already installed on this machine (that's why
this command exists), so your job now is to run the full mise flow against this project.
Load the canonical instructions, then follow them in full. The authoritative mise behavior — the prime directives, the Phase 0 mode detection (new setup vs. Rescue vs. Update), every phase, and the whole safety contract — lives in the vendored mise prompt. This command is only a thin launcher: it does not restate that content, so you must read it live (one source of truth, no forked copy that rots).
Find the prompt in this order and read the first that exists:
./.claude/mise-PROMPT.md— project-local install~/.claude/mise-PROMPT.md— global install- If neither exists, fall back to the network copy: read
https://raw.githubusercontent.com/emadd/mise-en-claude/main/PROMPT.mdand follow it. Tell the user you're using the network copy because no vendored prompt was found, and offer to re-run mise'sinstall.shso it's local next time.
If you cannot read it by any of those three routes, STOP and tell the user how to repair the install — do not improvise the setup from memory. A half-remembered mise is exactly the unsafe, non-consensual behavior mise exists to prevent.
Once loaded, execute the prompt exactly — same consent-first, snapshot-first, non-destructive, secrets-by-reference contract; let its Phase 0 detect the mode. Two things are already true because you arrived via the installed command, so act on them instead of re-deriving them:
- The workflow commands are already installed.
/mise-cook,/mise-handoff, and/mise-cleanexist on this machine. In the Skills + shortcuts phase, verify they're present and current rather than reinstalling from scratch. $ARGUMENTS, if given, is the user's steer — e.g.update,rescue, "just re-audit CLAUDE.md". Honor it over your own mode guess, but still run the version self-check and take the snapshot first — the steer changes what you do, never whether the work is safe.
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.
- 9d ago First seen · 39 lines · 47 tokens per session scan A 637725225f43
mise-init is a command published in the GitHub repository emadd/mise-en-claude (51 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 640 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 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.