kg-lint

kg-lint is a command for coding agents from Ethics03/kgskill. It costs 16 tokens per session (609 once invoked), scanned A, original, MIT.

A health check for a Knowledge Graph, meaning a collection of linked research notes and summaries.

In plain words
What is it for?
Use it to inspect the quality of the graph and automatically fix simple problems when the fix option is provided.
Why use it?
It finds disconnected pages, conflicting claims, missing links, broken links, outdated sources, and gaps in the data.

Command

Part of the mykg plugin — 3 skills, 6 commands shipped together

Install

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.

agentmods
npx agentmods add commands/ethics03/kgskill/kg-lint
Clone the repo
git clone --depth 1 https://github.com/Ethics03/kgskill

Or install mykg, the plugin that ships this one along with the rest of its 3 skills, 6 commands.

Wrote 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.

agentmods badge for kg-lint

README.md
[![agentmods](https://agentmods.dev/badge/commands/ethics03/kgskill/kg-lint.svg)](https://agentmods.dev/commands/ethics03/kgskill/kg-lint)
Your own site
<a href="https://agentmods.dev/commands/ethics03/kgskill/kg-lint"><img src="https://agentmods.dev/badge/commands/ethics03/kgskill/kg-lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00609
Opus 5 $0.00008 $0.00304
Sonnet 5 $0.00003 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 5d ago against content hash dd4e36fa5c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kg-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 5d 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.

commands/kg-lint.md · 81 lines

What it actually says

Health check the Knowledge Graph. Find orphans, contradictions, missing cross-references, stale claims, and data gaps. If fix was passed as an argument, auto-fix simple issues.

Steps

1. Resolve KG path

Check in order: $MYKG_PATH env var → ~/.config/mykg/config~/.mykgrc → common locations (~/MyKG, ~/Dev/Obsidian/MyKG). If not found, tell the user to run /kg-setup first.

2. Orphan check

Read all .md files under wiki/. For each page, check whether any other wiki page links to it via [[PageName]]. Report pages with no inbound links.

3. Contradiction check

Scan wiki pages for explicit contradiction markers (contradicts, conflicts, vs, but). Also read related entity/concept pages and flag where the same claim appears with different values.

4. Missing cross-references

Find entity or concept names that appear as plain text in wiki pages but are never linked as [[wikilinks]]. These are candidates for adding links.

5. Broken wikilinks

Find all [[links]] in wiki pages and check if the target file exists. Report any that point to missing pages.

6. Stale claims

Check source dates in frontmatter. Flag claims sourced only from old entries where newer sources on the same topic exist.

7. Data gaps

Read Active.md for open questions. Read synthesis pages for unanswered questions. Flag sparse entity/concept pages (fewer than 2 sources).

8. Report

Output a structured lint report:

# KG Lint Report

## Summary
- Orphan pages: X
- Contradictions: X
- Missing cross-refs: X
- Broken wikilinks: X
- Stale claims: X
- Data gaps: X

## Orphan Pages
- [[wiki/X]] — no inbound links

## Contradictions
- [[wiki/A]] and [[wiki/B]] conflict on <claim>

## Missing Cross-References
- "Term X" appears in [[wiki/Y]] but has no link

## Broken Wikilinks
- [[wiki/Missing]] referenced in [[wiki/Z]]

## Stale Claims
- [[concepts/X]] last sourced YYYY-MM-DD

## Data Gaps
- [[concepts/Y]] has only 1 source

## Recommendations
1. ...

9. Fix mode

If fix argument was given, auto-fix only:

  • Add missing wikilinks for clearly matched pages
  • Update updated frontmatter dates on modified pages

Do NOT auto-fix contradictions (require judgment) or data gaps (need new sources).

Changes

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.

  1. 5d ago First seen · 81 lines · 16 tokens per session scan A dd4e36fa5c51

Subscribe to this mod's changes

kg-lint is a command published in the GitHub repository Ethics03/kgskill (3 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 609 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.