SkillOpt is a tool for improving reusable natural-language skills used by fixed-weight language-model agents through training runs, trajectory-based edits, validation checks, and generated best_skill.md files. It is intended for developing, evaluating, and deploying agent skills without changing the underlying model weights. Catalogue add-ons support SkillOpt workflows and integrations with coding agents.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add microsoft/SkillOpt/plugin install skillopt-sleepWrote 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/microsoft/skillopt/skillopt-sleep)<a href="https://agentmods.dev/commands/microsoft/skillopt/skillopt-sleep"><img src="https://agentmods.dev/badge/commands/microsoft/skillopt/skillopt-sleep/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/microsoft/skillopt/skillopt-sleep"><img src="https://agentmods.dev/badge/commands/microsoft/skillopt/skillopt-sleep.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 | $0.00035 | $0.01149 |
| Opus 5.5 | $0.00014 | $0.00460 |
| Sonnet 5.5 | $0.00007 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
skillopt-sleep 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skillopt-sleep — SkillOpt-Sleep nightly self-evolution
You are driving SkillOpt-Sleep: a tool that lets this user's Claude agent
improve from past usage by reviewing sessions, replaying recurring tasks, and
consolidating what it learns into validated memory (CLAUDE.md) and skills
(SKILL.md). With the default gate enabled, a change is kept only if it improves
a held-out replay score. Nothing live is modified until adoption unless the
user explicitly requests --auto-adopt.
Requested action: $ARGUMENTS
(If $ARGUMENTS is empty, treat it as status.)
How to run it
The engine is the skillopt_sleep Python package in this repo. Split
$ARGUMENTS into the first action token and its remaining options, then use the
plugin's bundled runner so the right interpreter and repo are on the path.
Preserve the user's remaining options (for example --preferences, --backend,
or --target-skill-path) instead of silently dropping them:
"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" <action> --project "$(pwd)" --scope invoked <remaining options>
<action> is one of:
| action | what it does |
|---|---|
status |
show how many nights have run + the latest staged proposal (READ-ONLY) |
dry-run |
harvest → mine → replay → report, but stage nothing (no-staging preview) |
run |
full cycle: stage a validation report and any accepted proposal; only explicit --auto-adopt may also update live files |
adopt |
apply the latest staged proposal to live CLAUDE.md / SKILL.md (backs up first) |
harvest |
debug: print the recurring tasks mined from recent sessions |
schedule |
install a nightly cron entry for this project (--hour --minute, off-:00 by default) |
unschedule |
remove the nightly cron entry (--all to remove every managed entry) |
Default backend is mock (deterministic, no API spend). To use real budget for
model-driven optimization, add --backend claude or --backend codex. An
accepted gain is evidence on this run's held-out tasks, not a guarantee of
general improvement; results depend on the tasks, model, and checks. To steer
what the optimizer writes, add --preferences "<your house rules>".
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.
- 1mo ago First seen · 86 lines · 35 tokens per session scan A 3f3504ca2d5e
skillopt-sleep is a command published in the GitHub repository microsoft/SkillOpt (18,517 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,149 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.