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 klimentij/klimkit --skill klimkit-harness-cleanupgit clone --depth 1 https://github.com/klimentij/klimkitWrote 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/klimentij/klimkit/klimkit-harness-cleanup)<a href="https://agentmods.dev/skills/klimentij/klimkit/klimkit-harness-cleanup"><img src="https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-harness-cleanup/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/skills/klimentij/klimkit/klimkit-harness-cleanup"><img src="https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-harness-cleanup.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 | $0.00083 | $0.01140 |
| Opus 5 | $0.00042 | $0.00570 |
| Sonnet 5 | $0.00017 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
klimkit-harness-cleanup 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Cleanup
Use a two-key process: discovery produces stable action IDs; explicit user approval unlocks only those IDs. Treat each machine as an independent transaction.
Phase 1 — Discover, Research, Report
-
Register targets. List every local machine, SSH host, container, and VM in scope with its transport, OS, user/home, repository roots, and available privilege boundary. Ask only when the target set cannot be inferred safely.
- Complete when every requested target is reachable or marked blocked with the exact reason.
-
Refresh the surface map. Read references/surface-map.md, detect installed Codex and Claude versions, and verify current discovery/configuration locations against official vendor documentation. Add version-specific or organization-managed surfaces before scanning.
- Complete when every harness/version has dated source URLs and a search plan covering user, project, system, plugin, and runtime layers.
-
Collect metadata read-only. Run
scripts/inventory.pylocally on each target, transferring it ephemerally when necessary. Supplement it with read-only service/scheduler, process, package, environment-name, repository, worktree, symlink, and disk-usage checks. Record names, paths, hashes, ownership, tracking, precedence, and activation evidence; never emit secret values or configuration bodies from sensitive files.- Complete when every target and declared repository root is accounted for and scan gaps are explicit.
-
Classify every row. Use
authoritative,active,derived,cache,evidence,state,credential, orunknown. RecommendKEEP,QUARANTINE,DELETE,REMOVE_IN_CANONICAL_REPO, orMANUAL_REVIEW, with reason, risk, rollback, and a stable action ID. Group duplicates by origin and hash; distinguish files that exist from configuration proven active.- Complete when every artifact and repository row has one recommendation and every mutation candidate has an action ID.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 56 lines · 83 tokens per session scan A 3779d5635aab
klimkit-harness-cleanup is a skill published in the GitHub repository klimentij/klimkit (7 stars, last pushed 29d ago), licensed MIT. It adds 83 tokens to every session and 1,140 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 2026-08-31.
Other skills, from other repositories
LinkedIn automation via the Linked API CLI - fetch profiles, search people and companies, send messages, manage connections, create posts, react, comment, and run Sales Navigator and custom workflows. Use when the user wants to interact with LinkedIn.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-researcher
Organize research — manage references, notes, and collaboration.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.