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 commands/brentmitchell25/mise-plugin/update-skillgit clone --depth 1 https://github.com/brentmitchell25/mise-pluginWhat 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 | $0.00000 | $0.01952 |
| Opus 5 | $0.00000 | $0.00976 |
| Sonnet 5 | $0.00000 | $0.00390 |
| Haiku 4.5 | $0.00000 | $0.00195 |
Grade A, and why
update-skill 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update the mise plugin's SKILL.md by crawling the latest mise documentation using parallel research agents.
Process
- Read the current
skills/mise/SKILL.mdto understand the existing structure - Establish the "since last update" baseline: run
git log -1 --format=%cd --date=short -- skills/mise/SKILL.mdfor the last-update date (and note the currentversionin.claude-plugin/plugin.json) - Launch 6 parallel research agents — 5 documentation crawlers plus 1 release-notes auditor
- After all agents return, consolidate findings into an updated SKILL.md
- Run the
mise run linttask to validate the result
Research Agents
Launch ALL 6 of these agents in parallel using the Agent tool. Agents 1–5 use WebFetch to crawl the specified doc pages; Agent 6 uses the gh CLI to audit release notes. Each returns a structured summary of everything it finds.
Agent 1: Tasks (TOML + File)
Crawl these pages and return all task-related documentation:
- https://mise.jdx.dev/tasks/toml-tasks.html
- https://mise.jdx.dev/tasks/file-tasks.html
- https://mise.jdx.dev/tasks/task-configuration.html
Focus on: all task fields (especially new ones), structured run/depends syntax, extends/inheritance, timeout, file task headers (#MISE/#USAGE), remote tasks, task namespacing, CLI flags for mise run, output modes. Return every field name, type, and default value you find.
Agent 2: Dev Tools & Backends
Crawl these pages and return all dev tool documentation:
- https://mise.jdx.dev/dev-tools/
- Follow links to individual backend pages (aqua, github, npm, cargo, pipx, etc.)
Focus on: all backends with their specific options, per-tool options (version, os, postinstall, install_env), TOML syntax variants (simple string, array, table), version formats (exact, prefix, latest, ref, path, sub-N), shims vs PATH mode, aliases, registry, CLI commands (mise use, mise install, mise ls, mise ls-remote, mise which, mise x, mise reshim).
Agent 3: Environments & Settings
Crawl these pages and return all environment/settings documentation:
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 · 119 lines · 0 tokens per session scan A d4618b25eea5
update-skill is a command published in the GitHub repository brentmitchell25/mise-plugin (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,952 tokens. 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.