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 yasik/kmd --skill kmd-lintgit clone --depth 1 https://github.com/yasik/kmdWrote 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/yasik/kmd/kmd-lint)<a href="https://agentmods.dev/skills/yasik/kmd/kmd-lint"><img src="https://agentmods.dev/badge/skills/yasik/kmd/kmd-lint/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/yasik/kmd/kmd-lint"><img src="https://agentmods.dev/badge/skills/yasik/kmd/kmd-lint.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 | $0.00102 | $0.01549 |
| Opus 5 | $0.00051 | $0.00775 |
| Sonnet 5 | $0.00020 | $0.00310 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
kmd-lint 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 8d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kmd-lint — KB health check
A knowledge base rots by default: indexes drift from pages, claims go stale, duplicates accumulate, sources pile up un-ingested. Lint is the counter-force and it is not optional — every production implementation of the LLM-wiki pattern reports drift as the failure mode. Lint runs in two phases: deterministic checks (a script — free, exhaustive) and judgment passes (you — expensive, so spent only where scripts can't reach).
Before you start
Locate the KB root and transport the same way kmd-ingest does (its
references/obsidian-cli-transport.md covers the Obsidian CLI, whose
backlinks/orphans/unresolved commands can corroborate graph
findings when available): a path you were given >
$KMD_ROOT > .kmd.json at the workspace root > a directory containing
schema.md/log.md > the default kb/. The script's --kb flag implements
this resolution. Then check for the org extension: if .kmd.json declares
an "org" key or the workspace has _charter/ORG.md, read
references/org-extension.md — it changes how
findings are routed in Phase 3. Otherwise the core protocol below applies
as written.
Phase 1 — mechanical checks (run the script first)
python3 scripts/lint_mechanical.py --kb <kb-root> --report --agent <your-name-or-agent-id>
This checks: broken wikilinks, invalid/missing frontmatter (including the
provenance rule), modified files under sources/ (append-only violation,
via git — when the KB is not under git the script says so explicitly rather
than implying coverage), unreferenced sources (un-ingested intake), orphan
pages, page updates with no LOG entry, oversized pages, and a missing or
stale index.md (fix: recompile_index.py from kmd-ingest). With
--report it writes a
report skeleton to <kb>/.lint/<date>-mechanical.md (or the report_dir
configured in .kmd.json) with empty Judgment findings and Resolution
sections for you to fill in. Use --format json to process findings
programmatically.
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.
- 8d ago First seen · 123 lines · 102 tokens per session scan A 1bd01b646eb9
kmd-lint is a skill published in the GitHub repository yasik/kmd (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,549 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
firebase-cloud-firestore
Use when setting up Firestore, designing schemas, doing CRUD, creating listeners, paginating queries, configuring indexes, enabling offline persistence, or writing security rules.
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
firebase-data-connect
Use when setting up Data Connect, writing GraphQL queries/mutations, configuring generated SDKs, handling offline, or applying security rules.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
status
Verify gnosis-mcp server connectivity, schema integrity, and corpus health. Use when MCP calls fail, return empty, or return unexpected data.
manage
CRUD operations on the knowledge base — add, delete, update metadata. For bulk ingest / re-ingest / prune, use /gnosis:ingest instead. Requires GNOSISMCPWRITABLE=true.