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 skills add kensaurus/cursor-kenji --skill housekeep-gatesgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/skills/kensaurus/cursor-kenji/housekeep-gates)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/housekeep-gates"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/housekeep-gates.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.01899 |
| Opus 5 | $0.00040 | $0.00949 |
| Sonnet 5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
housekeep-gates 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 4d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
housekeep-gates — One required check, defined in code
Degree of freedom: MIXED — T1 is the priority. Mapping and winner
confirmation [HIGH freedom]; aggregator needs: + skip-fail, loser
deletion, branch-protection, and Phase 4 probes [LOW freedom — run exactly]. Net enforcement strictly ≥ before.
Apply-now. audit-gate-logic mapped the sprawl and named a winner per
duplicate cluster; this makes the repo match the map. Target state: one
required check in branch protection, backed by an aggregator job that
needs: every real gate — so "what blocks merge" has exactly one answer,
in one file.
Every retirement is proven safe before deletion. Never weaken enforcement while consolidating. Net enforcement strictly ≥ before.
This is the execution arm of audit-gate-logic, the same way
housekeep-design executes plan-uiux-unification.
This skill vs neighbors
| Skill | Owns |
|---|---|
| housekeep-gates (this) | Consolidate / delete / wire the aggregator |
audit-gate-logic |
Read-only map — bypass, ratchets, archaeology |
audit-cicd |
Pipeline cost, speed, storage |
workflow-quality-gate |
Runs the pre-release sweep |
enhance-agent-guardrails |
Installs new guard classes, not accreted-gate cleanup |
workflow-green-repo |
Make the repo green — does not redesign the gate graph |
housekeep-backlog |
Parked-work register — not CI gates |
How to reason
- Observe — archaeology map: cluster, winner, loser, current required checks
- Interpret — would deleting this loser drop unique coverage?
- Classify — port-then-delete / keep / not-yet-mapped
- Severity — deleting the only server-side-enforced gate is a regression
Worked example
Observe: two lint jobs; old
lint.ymlis required; newci.ymllint is not.paths:skips.github/**. Interpret: retiringlint.ymlwithout porting + aggregator skip-fail would let a workflow edit merge unlinted. Classify: port unique rules, wire winner, delete loser; probe the skip path. Probe: change matching the old skip filter → aggregator must go red, not skip-green.
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.
- 4d ago First seen · 174 lines · 80 tokens per session scan A 79eb61778f8a
housekeep-gates is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 1,899 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
production-release-gating
Stop every push/merge to main from shipping to production — deploy only on a real release. Use when a merge to main unexpectedly deploys to prod, when you want production to deploy only on a semantic-release version (not every commit), when setting up preview-on-feature-branch but gated-prod-on-main, wiring a Vercel…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
git-master
Handles git work: atomic commits, rebase, squash, blame, bisect, reflog, and history questions. Use whenever a task needs a commit or a git-history investigation; skip for ordinary code edits.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what changed, whats new.