A semantic linter for a business-idea wiki. Unlike a basic link checker, it reviews whether claims are supported, sourced, clear, and consistent.

Use it to inspect wiki overviews and deep-dive notes, check citations and claim labels, compare risks with verdicts, and identify completed or unvalidated assumptions.

It helps find stale, unsupported, ambiguous, or contradictory information before it is treated as reliable.

wiki-lint — Skill for Claude Code and Codex by schub-tech

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.

Any agent

npx skills add schub-tech/llm-ideation-wiki --skill wiki-lint

Clone the repo

git clone --depth 1 https://github.com/schub-tech/llm-ideation-wiki

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/wiki-lint/github.svg)](https://agentmods.dev/skills/schub-tech/llm-ideation-wiki/wiki-lint)

Your own site

<a href="https://agentmods.dev/skills/schub-tech/llm-ideation-wiki/wiki-lint"><img src="https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/wiki-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/schub-tech/llm-ideation-wiki/wiki-lint"><img src="https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/wiki-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 576 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00576
Opus 5.5	$0.00018	$0.00230
Sonnet 5.5	$0.00009	$0.00115
Haiku 4.5	$0.00004	$0.00058

Measured 22d ago against content hash f76239d8200c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wiki-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 22d 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.

.agents/skills/wiki-lint/SKILL.md · 47 lines

What it actually says

Run a semantic lint pass over the business-idea wiki. This complements the Notion helper checks in docs/agent/workflows.md; it does not replace them.

Start with deterministic checks.

Run the deterministic Notion helper checks from docs/agent/workflows.md.
Read the relevant Notion idea page before reading deep-dive pages.

Semantic checks. For each idea, inspect the overview and its related deep-dive notes for:

Unsupported material claims. Any statistic, price, legal statement, named competitor claim, market-size claim, or dated event must have a raw-source line citation.
Unmarked synthesis. Claims that are inferred from multiple sources, not directly stated by one source, should carry ^[inferred].
Ambiguity drift. Contested or weak claims should carry ^[ambiguous] and should not be written as settled.
User-only premises. Founder assertions, anecdotes, and "everyone says yes" style evidence should carry ^[user-claim] unless independently validated.
Risk/verdict mismatch. If a risk could kill the idea, the verdict and Next moves must reflect it.
Answered validations. If a Still to validate item is already answered in a deep-dive or raw note, update or remove it.
Stale claims. Pages older than 90 days should be checked for date-sensitive claims before being treated as current.
Mapping mismatch. Notion pages that should be script-addressable should either be added to notion.config.json or explicitly left as manually navigated child pages.
Prose bloat. Flag any sentence over ~20 words, any bullet carrying two claims, and any run of more than ~3 sentences of prose. Rewrite to the ## Output rules in AGENTS.md.

Report format. Lead with the highest-severity findings:

## Semantic Lint

### P1
- [Page](path) — claim/risk. Why it matters. Suggested fix.

### P2
- ...

### Maintenance
- Mapping/index/log/hot-cache updates needed.

Use priorities this way:

P1: Could change the verdict or invalidate a next move.
P2: Material but not immediately verdict-changing.
P3: Hygiene, clarity, or future retrieval quality.

If the user asked you to fix issues, edit the Notion wiki directly, then run the ritual (AGENTS.md § Mechanics).

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.

22d ago Changed f76239d8200c
2mo ago First seen · 47 lines · 44 tokens per session scan A 70e8808aeeea

Subscribe to this mod's changes

wiki-lint is a skill published in the GitHub repository schub-tech/llm-ideation-wiki (12 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 576 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 2026-08-30.

Claude Code LLM Research agent-skills entrepreneurship founders idea-validation

wiki-lint next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wiki-lintschub-tech/llm-ideation-wiki	Skill	12	22d ago	MIT	A	44	Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agent	Skill	261k	today	MIT	A	17	Claude Code, Codex
mcporterNousResearch/hermes-agent	Skill	261k	today	MIT	A	16	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	today	Apache-2.0	A	217	Claude Code, Codex
safe-refactorJuliusBrussee/caveman	Skill	118k	today	Apache-2.0	A	29	Claude Code, Codex
create-tech-designhumanlayer/humanlayer	Skill	13k	yesterday	Apache-2.0	A	16	Claude Code, Codex
deploy-docker-composeomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	84	Claude Code, Codex