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/microsoft/skillopt/skillopt-sleep-handoffgit clone --depth 1 https://github.com/microsoft/SkillOptWhat 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 | $0.00037 | $0.00894 |
| Opus 5 | $0.00018 | $0.00447 |
| Sonnet 5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
skillopt-sleep-handoff 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skillopt-sleep-handoff — session-executed sleep cycle
You are driving SkillOpt-Sleep in handoff mode: the Python engine runs
every deterministic stage (harvest → mine → replay scoring → gate → stage)
and outsources each model call (attempt / judge / reflect) to YOU via
prompt files. No claude -p subprocess, no API key — the model work runs
on this session's budget, but each prompt MUST be answered in a fresh,
isolated context so the validation gate stays honest.
Requested action: $ARGUMENTS
(If $ARGUMENTS is empty, treat it as run.)
The loop
Repeat until the engine exits 0 (done) — at most 8 rounds:
-
Run the engine via the bundled runner. Split
$ARGUMENTSinto the action and remaining options, and preserve those options on every resumed round:"${CLAUDE_PLUGIN_ROOT}/scripts/sleep.sh" <action> --backend handoff --project "$(pwd)" --scope invoked <remaining options>- exit 0 → the night is complete; go to "Finish" below.
- exit 3 → pending model calls; continue with step 2.
- anything else → stop and show the user the error output.
-
Read the batch:
Read.skillopt-sleep-handoff/pending.jsonin the project. Each entry hasid,prompt,max_tokens,answer_file. -
Answer each prompt in ISOLATION — this is the integrity rule:
- For each entry, launch a subagent (Task tool) whose ENTIRE input is
the
prompttext verbatim. Add nothing: no summary of this session, no mention of SkillOpt, no other prompts from the batch. - Take the subagent's reply and
Writethe raw answer text (no commentary, no code fences) to the entry'sanswer_file. - NEVER answer from this session's own context — you have seen the mined tasks and their references, so inline answers would contaminate the held-out gate and fake the improvement score.
- For each entry, launch a subagent (Task tool) whose ENTIRE input is
the
-
Re-run the same engine command — it resumes from the answers directory and either finishes or stages the next batch.
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 · 76 lines · 37 tokens per session scan A 5d1c31afb0b0
skillopt-sleep-handoff is a command published in the GitHub repository microsoft/SkillOpt (16,591 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 894 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.