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 xz1220/Kempt --skill kempt-cleangit clone --depth 1 https://github.com/xz1220/KemptWrote 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/xz1220/kempt/kempt-clean)<a href="https://agentmods.dev/skills/xz1220/kempt/kempt-clean"><img src="https://agentmods.dev/badge/skills/xz1220/kempt/kempt-clean/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/xz1220/kempt/kempt-clean"><img src="https://agentmods.dev/badge/skills/xz1220/kempt/kempt-clean.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 | $0.00090 | $0.00653 |
| Opus 5 | $0.00045 | $0.00327 |
| Sonnet 5 | $0.00018 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
kempt-clean 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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kempt Clean — reversible cleanup with undo
You are applying Kempt's clean plan with the user's explicit confirmation. Every change is reversible: items move to Kempt's recycle bin and the whole batch can be undone with one command. You never hard-delete anything.
Steps
-
Locate the CLI (same as kempt-checkup):
command -v kempt, elsenode <kempt-repo>/bin/kempt.mjs. -
Ensure a fresh report. If the user just ran a checkup, reuse it. Otherwise run
kempt scan --jsonfirst — the clean plan is derived from the latest report. -
Dry-run and show the plan. Run:
kempt clean(no
--yes→ dry run, nothing is touched). Summarize for the user what would be cleaned: each item'swhat,detail, size, and that all of it goes to the recycle bin. By default this coverssafe-group items only; mention that--allwould also include manual-review items such as the memory merge. -
Ask the user to confirm. Show the item list and ask explicitly. Respect their choice; they can also cherry-pick with
--items <id,id>(ids are shown bykempt plan). -
Apply only after a clear yes:
kempt clean --yes --jsonReport back: items cleaned, bytes reclaimed, health score before → after.
-
Always end with the undo path:
kempt restore --lastundoes the entire batch;
kempt historyshows what is in the recycle bin and until when it can be restored.
Rules
- Never run
kempt clean --yeswithout the user's explicit confirmation in this conversation. A standing instruction like "clean everything from now on" from a prior session does not count. - Never run
kempt empty-recycleunless the user explicitly asks to permanently empty the recycle bin — it is the only irreversible command. Warn before running it. - Do not edit, move or delete any file under
~/.claude/~/.codexyourself; the only write path is the Kempt CLI, which guarantees reversibility. - If a restore or clean fails, surface the CLI's error verbatim and stop; do not improvise
with
rm/mv.
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.
- 11d ago First seen · 62 lines · 90 tokens per session scan A 1e0d5b471a1d
kempt-clean is a skill published in the GitHub repository xz1220/Kempt (2 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 653 once invoked, about $0.0005 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
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
init
Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
rekal
Use in a repo with Rekal initialized (.rekal/ exists). Rekal is memory of prior AI sessions — who changed what, why, and when. Before spending a token, decide WHERE the answer lives: TREE / KNOWLEDGE / LEDGER / MAP. Route to one substrate, act, and stay silent when memory is not the tool. Rekal's commands return…
claude-compaction-restore
Use when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /compact, or needs to rebuild its working mental model from Claude JSONL transcripts and touched files.