菜单
Measure and defend the always-loaded context budget (CLAUDE.md + unscoped rules). A self-improving harness accretes rules and lessons over time; without this regulator it silently bloats until instruction-following degrades. Run periodically, after adding rules, or when CLAUDE.md grows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or upgrade a self-improving Claude Code harness in the current project — self-healing failure ledger, per-file lesson memory, regression evals, small-model elevation agents, deterministic safety hooks. Modes: (no args) auto-detect new vs upgrade; 'doctor' = validate only. Evidence-gated: scan, propose plan, confirm, apply, verify.
Self-maintenance pass over the .claude/ harness itself: validate every mechanical invariant, detect drift and dead weight, and propose upgrades. Run periodically, after any harness change, or via /loop.
Run one iteration of this project's maintenance loop: finish in-flight work, convert failures into lessons, checkpoint hygiene, audit the harness, or start the next pending task — whichever is highest-value right now. Also the remedy when capability-gate.sh blocks a source edit because maintenance is overdue.
Remove dead code, unused dependencies, commented-out blocks, and orphaned files once a checkpoint is reached — for long-term maintainability. Evidence-gated and reversible: nothing is removed without proof it is unreferenced, and build+tests must stay green after every batch. Run after a milestone/feature completes, not mid-implementation.
Convert this session's failures and user corrections into durable per-file lessons in .claude/memory/lessons/, following the evidence-backed write policy (retrieve-similar-first, delta updates, weighted vote lifecycle, hook promotion). Run at the end of any session that contained a correction or a repeated failure.
Holistic, single-pass senior-engineer review of the target project's actual code (not the harness) across security, performance, code quality, and production-readiness. Use for 'is this ready to ship', a full code review, a security audit, or a performance pass.
| name | context-budget |
| description | Measure and defend the always-loaded context budget (CLAUDE.md + unscoped rules). A self-improving harness accretes rules and lessons over time; without this regulator it silently bloats until instruction-following degrades. Run periodically, after adding rules, or when CLAUDE.md grows. |
| allowed-tools | Bash(bash .claude/scripts/context-budget.sh), Read, Grep, Glob |
The regulator for the harness's own context cost. Always-loaded content (CLAUDE.md + every .claude/rules/*.md without a paths: frontmatter) is paid on every turn; instruction-following measurably decays as it grows, and small models degrade fastest — so this must stay small. Path-scoped rules and skills/agents cost nothing until triggered and don't count.
bash .claude/scripts/context-budget.sh. It prints each always-loaded file's token estimate, the total, and a PASS / NEAR LIMIT / OVER BUDGET verdict (target ≤1200, hard cap ≤1500)..claude/HARNESS.md) or the relevant skill. CLAUDE.md should be a ~25-line index of pointers, not prose. This is almost always the biggest contributor.paths: ["glob"] frontmatter so it loads only when Claude reads a matching file.Wire bash .claude/scripts/context-budget.sh into CI so a future rule/lesson addition can't silently blow the budget.