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-doctorgit 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-doctor)<a href="https://agentmods.dev/skills/underpass-ai/kmp/kmp-doctor"><img src="https://agentmods.dev/badge/skills/underpass-ai/kmp/kmp-doctor/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-doctor"><img src="https://agentmods.dev/badge/skills/underpass-ai/kmp/kmp-doctor.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 | $0.00050 | $0.00452 |
| Opus 5.5 | $0.00020 | $0.00181 |
| Sonnet 5.5 | $0.00010 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
kmp-doctor 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 1mo 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 doctor
Resolve the plugin root as two directories above this SKILL.md and run
<plugin-root>/scripts/kmp-doctor.sh. This is the primary doctor because it
checks the binary and store plus effective Claude/Codex wiring, retired tool
policies, and plugin/global MCP ownership.
Only if the bundled script is unavailable, fall back to kmp-mcp doctor and
state explicitly that host wiring and ownership were not checked.
Show the first branded block verbatim. Then give the usable/not-usable verdict, the first blocking cause, and the exact repair named by the doctor. Preserve warnings about fixture mode, stale sessions, retired tool-name policies, plugin/global MCP ownership collisions, and a lexical-bridge table the store ignored: a malformed table means Ask quietly stopped crossing languages.
Keep three host facts apart when you report them; the doctor prints them as three separate lines and collapsing them hides the failure:
- the plugin is installed and enabled in that host;
- the engine binary declares its tools, proved by running the executable directly against a scratch directory — not evidence of a host connection;
- a host reports a live MCP connection. Only that line is verification. Where no live probe ran, the doctor says unverified, which is a warning, not an approval. Report it as unverified: a registration an inventory knows about is not a conversation that can call a tool.
The Memory section names the winning selection rule and the whole precedence.
When the selected memory cannot be opened, report the reason and the repair the
doctor printed. Never suggest migrating or replacing a store: KMP refuses an
incompatible one and leaves every file in it untouched, and choosing another
directory with kmp-mcp config memory-store <absolute-path> — or
--clear for automatic selection — is the user's decision to make.
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.
- 1mo ago Changed · +18 lines 9bb68d3d4aa4
- 1mo ago Changed · +1 lines 218252f84817
- 1mo ago First seen · 20 lines · 50 tokens per session scan A 4c1e7321c9fd
kmp-doctor is a skill published in the GitHub repository underpass-ai/kmp (0 stars, last pushed 18d ago), licensed Apache-2.0. It adds 50 tokens to every session and 452 once invoked, about $0.0002 per session on Opus 5.5. 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
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
titen-memory
Use the Titen MCP server to recall bounded evidence-grounded context, record verified durable signals, submit feedback, and coordinate checkpoints, leases, or handoffs. Use when work may benefit from prior project memory or when a verified outcome should be preserved for another agent; do not use it to capture raw…
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
continual-learning
Mine chat transcripts for decisions, exec updates, strategy shifts, feedback themes, and user preferences. Write structured entries to memory/, then update AGENTS.md with curated preferences and facts. The ingestion pipeline for the PM-OS context graph.
knowledge-updater
Update knowledge layer docs with automatic versioning. Use when updating strategy, segments, metrics, or competitive landscape. Snapshots the current state before overwriting so the retrospective agent can detect strategy drift.
context-engineer
Context window optimizer — analyze, audit, and optimize your agent's context utilization. Know exactly where your tokens go before they're sent.