Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-knowledgeWrote 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/cogni-work/insight-wave/knowledge-distill)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-distill"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-distill/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/cogni-work/insight-wave/knowledge-distill"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-distill.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 | $0.00200 | $0.12224 |
| Opus 5.5 | $0.00080 | $0.04890 |
| Sonnet 5.5 | $0.00040 | $0.02445 |
| Haiku 4.5 | $0.00020 | $0.01222 |
Grade A, and why
knowledge-distill 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.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Distill
Phase 4.5 of the inverted pipeline — it sits between knowledge-ingest (Phase 4) and knowledge-compose (Phase 5): plan → curate → fetch → ingest → **distill** → compose → verify → finalize.
Phase 4 deposits one type: source page per fetched URL (verbatim body + pre_extracted_claims:). That makes the wiki a citation store. This phase turns those source claims into the distilled concept/entity web that makes a Karpathy wiki compound across runs: type: concept / type: entity pages that successive runs enrich (new claims appended, source backlinks unioned) rather than duplicate, with claim-level dedup at deposit and per-run re-narration of updated summaries (Step 6.7) so the wiki compounds narratively — the entry-point prose integrates new evidence — as well as structurally. The differentiation thesis's compounding loop + claims-dedup metric become real here.
Optional + fail-soft — at every hop. A distill failure must NEVER block knowledge-compose. Same posture as the knowledge-curate Step 0.5 coverage pre-step: warn loudly, exit cleanly, let the pipeline continue. This governs every step below unless that step says otherwise: an agent returning ok: false, a missing/empty records file, or a non-zero merge-script exit each warns (surfacing the error) and continues to the next step with prior state intact. The concept/entity pages are an enrichment layer, not a correctness gate.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 4.5 — knowledge-distill" once to anchor on the contract.
When to run
<project>/.metadata/ingest-manifest.jsonexists with non-emptyingested[](Phase 4 has run).- User explicitly invokes
/cogni-knowledge:knowledge-distill, or the pipeline reaches Phase 4.5.
Never run when
- No
<project>/.metadata/ingest-manifest.jsonoringested[]empty — offerknowledge-ingestfirst (but do NOT hard-fail the pipeline; distill is optional). - No
binding.jsonat the resolved knowledge root — offerknowledge-setupfirst. binding.wiki_pathdoes not resolve to a directory containing.cogni-wiki/config.json— the binding is stale.
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 · -8 lines 69811dd4e22a
- 1mo ago First seen · 507 lines · 200 tokens per session scan A a0f6ecb48d56
knowledge-distill is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 200 tokens to every session and 12,224 once invoked, about $0.0008 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…