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 underpass-ai/kmp --skill kmp-uninstallgit clone --depth 1 https://github.com/underpass-ai/kmpWrote 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/underpass-ai/kmp/kmp-uninstall)<a href="https://agentmods.dev/skills/underpass-ai/kmp/kmp-uninstall"><img src="https://agentmods.dev/badge/skills/underpass-ai/kmp/kmp-uninstall/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/underpass-ai/kmp/kmp-uninstall"><img src="https://agentmods.dev/badge/skills/underpass-ai/kmp/kmp-uninstall.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 | $0.00021 | $0.00453 |
| Opus 5 | $0.00010 | $0.00227 |
| Sonnet 5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
kmp-uninstall 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 2d 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.
What it actually says
KMP uninstall
Run kmp-mcp uninstall as a dry run first. It is the unscoped command and it
proposes the whole installation, so never reach for it to remove one thing.
To retire one memory, use kmp-mcp uninstall --store <absolute-path>; to
remove one engine — the superseded copy doctor warns about — use
kmp-mcp uninstall --engine <absolute-path>. Either way the preview and the
apply cannot reach any other store, engine, plugin or host wiring. The selected
path must be an existing store or an engine named kmp-mcp. Never add
--apply or --purge unless the user explicitly requested it; --purge skips
the protective export.
An apply must refuse an active store and leave every process running. Tell the user which owning host must be stopped or restarted; never kill it on behalf of uninstall. Retry only after that host releases the store. Name the export path and restore command.
The preview distinguishes held from kept. held names a host and process
still reading that piece: it is ours, it is a restart away, and uninstall will
not end the process to get at it. kept is final here — the piece was never
this verb's to remove. Report the two differently; a reader told only that
something was kept has no next step.
Lines labelled leftover are what the retired standalone wiring left behind —
Codex /kmp- prompts and the shell scripts beside a standalone engine. Nothing
running reads them. They are safe to remove even while the plugin installation
stays exactly as it is.
Use the unscoped command only when the user requested removal of the whole KMP
installation. Remove host wiring only from its owner: codex plugin remove for
plugin-managed installs, or the global MCP and standalone assets for
standalone installs. Do not remove both paths when only one owns the
installation.
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.
- 2d ago Changed · +16 lines 605d5884b88a
- 8d ago First seen · 24 lines · 21 tokens per session scan A e41bcc94d3aa
kmp-uninstall is a skill published in the GitHub repository underpass-ai/kmp (0 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 453 once invoked, about $0.0001 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.