knowledge-verify

knowledge-verify is a skill for Claude Code, Codex from cogni-work/insight-wave. It costs 155 tokens per session (10,439 once invoked), scanned A, original, Apache-2.0.

A claim-checking step that compares citations in a draft with the saved claims on the cited source pages.

In plain words
What is it for?
Use it to verify research drafts, classify citations as matching or unsupported, and revise unsupported statements before finalizing the document.
Why use it?
It catches statements that are not supported by their cited evidence and gives the draft a limited chance to be revised, without making new network requests.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cogni-knowledge plugin — 23 skills, 16 agents 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 skills/cogni-work/insight-wave/knowledge-verify
Any agent
npx skills add cogni-work/insight-wave --skill knowledge-verify
Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Made for: Claude Code, Codex.

Or install cogni-knowledge, the plugin that ships this one along with the rest of its 23 skills, 16 agents.

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 knowledge-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-verify.svg)](https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-verify)
Your own site
<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-verify"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,439 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 $0.00155 $0.10439
Opus 5 $0.00077 $0.05220
Sonnet 5 $0.00031 $0.02088
Haiku 4.5 $0.00015 $0.01044

Measured 3d ago against content hash cedd6a3eab26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-verify 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 3d 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.

cogni-knowledge/skills/knowledge-verify/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Verify

Phase 6 of the inverted pipeline. Reads <project>/output/draft-vN.md + <project>/.metadata/citation-manifest.json, dispatches wiki-verifier once per round to score every citation against each cited page's pre_extracted_claims:, and loops with revisor on unsupported deviations — capped at 2 revisor iterations per references/inverted-pipeline.md Phase 6.

Verifier verdicts: verbatim / paraphrase (evidence-aligned) and synthesis (informational, for claim_id: null citations to synthesis pages) go to verified[]. Only unsupported goes to deviations[] — that is the revisor's trigger. The loop terminates either when deviations[].verdict == "unsupported" is empty OR when revision_round == 2 is reached, whichever fires first.

This is the zero-network claim-alignment gate. The wiki has every source body verbatim under wiki/sources/<slug>.md with pre_extracted_claims: in frontmatter (the ingest phase wrote them at ingest time). The verifier does string-match scoring against those claims — no WebFetch, no re-extraction, no claims.json store.

verify-vN.json shape (written per round by wiki-verifier):

{
  "schema_version": "0.1.1",
  "draft_version": 1,
  "revision_round": 0,
  "verified": [
    {"id": "cit-001", "draft_position": "02:03", "wiki_slug": "eu-ai-act-article-6", "claim_id": "clm-001", "verdict": "paraphrase", "grounded": true}
  ],
  "deviations": [
    {"id": "cit-023", "draft_position": "03:07", "wiki_slug": "bitkom-gpai-position", "claim_id": "clm-004", "verdict": "unsupported", "grounded": false, "reason": "claim_text_misaligned", "note": "..."}
  ],
  "counts": {"verbatim": 4, "paraphrase": 28, "synthesis": 2, "unsupported": 3, "total": 37},
  "grounding_metrics": {"grounded": 28, "ungrounded": 6, "unscored": 3, "grounding_rate": 0.824}
}

Schema 0.1.1 is additive over 0.1.0: each verdict entry carries a per-citation grounded signal (true/false/null), and verify-store.py merge sums them into the headline grounding_metrics block (grounding_rate = grounded / (grounded + ungrounded), or null when nothing is scorable). A 0.1.0 reader simply ignores both — the draft↔excerpt grounding rate is pure observability, never a verify gate.

Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 6 — knowledge-verify" and references/claim-at-ingest.md once to anchor on the contract.

Read the full file on GitHub · 521 lines

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. 3d ago First seen · 521 lines · 155 tokens per session scan A cedd6a3eab26

Subscribe to this mod's changes

knowledge-verify is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 155 tokens to every session and 10,439 once invoked, about $0.0008 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens