SkillHub

context-clean-up

v1.0.7

Use when: prompt context is bloating (slow replies, rising cost, noisy transcripts) and you want a ranked offender list + reversible plan. Don't use when: you want automatic deletions or unattended config edits. Output: an audit-only report (top offenders + 3-8 lowest-risk fixes + rollback notes). N...

Sourced from ClawHub, Authored by phenomenoner

Installation

Please help me install the skill `context-clean-up` from SkillHub official store. npx skills add phenomenoner/context-clean-up

Context Clean Up (audit-only)

This skill identifies what is bloating prompt context and turns it into a safe, reversible plan.

Contract

  • Audit-only by default.
  • No automatic deletions.
  • No unattended config edits.
  • No silent cron/session pruning.
  • If you ask for changes, the skill should propose:
  • exact change,
  • expected impact,
  • rollback plan,
  • verification steps.

Safety model

  • No exec tool usage.
  • No read tool usage.
  • If you want file-level analysis, run the bundled script manually and paste the JSON.

Quick start

  • /context-clean-up → audit + actionable plan (no changes)

Optional manual report generation:

python3 scripts/context_cleanup_audit.py --out context-cleanup-audit.json

Windows variant:

py -3 scripts/context_cleanup_audit.py --out context-cleanup-audit.json

What to measure (authoritative, not vibes)

When available, prefer fresh-session /context json receipts over subjective claims like “it feels leaner”.

High-signal fields: - eligible skills - skills.promptChars - projectContextChars - systemPrompt.chars - promptTokens

If exact receipts are unavailable, fall back to ranked offenders + change scope, but label confidence lower.

Common offender classes

  1. Tool result dumps
  2. oversized exec output
  3. large read output

  4. long web_fetch payloads

  5. Automation transcript noise

  6. cron jobs that say “OK” every run

  7. heartbeat messages that are not alert-only

  8. Bootstrap reinjection bloat

  9. overgrown AGENTS.md / MEMORY.md / SOUL.md / USER.md

  10. long runbooks embedded directly in SKILL.md

  11. Ambient specialist surface

  12. too many always-visible specialist skills that should be on-demand workers/subagents instead

  13. Summary accretion

  14. repeated summaries that keep historical detail instead of restart-critical facts only

Phase 1 — Noise discipline

  • Make no-op automation truly silent (NO_REPLY or nothing on success).
  • Keep alerts out-of-band when possible.

Phase 2 — Bootstrap slimming

  • Keep always-injected files short.
  • Move long guidance to references/, memory/, or external notes.

Phase 3 — Ambient surface reduction

  • Remove low-frequency specialist skills from always-on prompt surface.
  • Prefer worker/subagent invocation for specialist flows.

Phase 4 — Higher-risk changes

  • Tool-surface or deeper runtime/config narrowing.
  • Only propose with stronger rollback and explicit approval.

Workflow (audit → plan)

Step 0 — Determine scope

You need: - workspace dir - state dir (<OPENCLAW_STATE_DIR>)

Common defaults: - macOS/Linux: ~/.openclaw - Windows: %USERPROFILE%.openclaw

Step 1 — Run the audit script

python3 scripts/context_cleanup_audit.py --workspace . --state-dir <OPENCLAW_STATE_DIR> --out context-cleanup-audit.json

Interpretation cheatsheet: - huge tool outputs → transcript bloat - many cron/system lines → automation bloat - large bootstrap docs → reinjection bloat

Step 2 — Produce a fix plan

Include: - top offenders - lowest-risk fixes first - expected impact - rollback notes - verification plan

Step 3 — Verify

After changes: - confirm automation is silent on success - check context growth flattens - if possible, compare fresh-session /context json before/after

Important caveat

Many OpenClaw runtimes snapshot skills/bootstrap per session. So skill/config slimming often does not fully apply to the current session. Use a new session for authoritative verification.

References

  • references/out-of-band-delivery.md
  • references/cron-noise-checklist.md