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-curate)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-curate"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-curate/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-curate"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-curate.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 | $0.00140 | $0.05640 |
| Opus 5.5 | $0.00056 | $0.02256 |
| Sonnet 5.5 | $0.00028 | $0.01128 |
| Haiku 4.5 | $0.00014 | $0.00564 |
Grade A, and why
knowledge-curate 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Curate
Phase 2 of the inverted pipeline. Reads <project>/.metadata/plan.json, fans out one source-curator dispatch per sub-question (WebSearch + scoring, then a WebFetch body-pull of each survivor into the shared fetch-cache), and merges the per-sub-question candidate batches into the canonical <project>/.metadata/candidates.json via candidate-store.py append-batch. Each merged candidate carries a fetch sub-object recording cache key / content hash on success or the unavailable reason on a WebFetch miss.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 2 — knowledge-curate" once to anchor on the contract.
When to run
plan.jsonexists for the project (Phase 1 has run) ANDcandidates.jsondoes not yet exist (or the user explicitly wants a re-curate)- User explicitly invokes
/cogni-knowledge:knowledge-curate
Never run when
- No
plan.jsonexists at<project_path>/.metadata/— offerknowledge-planfirst. - No
binding.jsonexists at the resolved knowledge root — offerknowledge-setupfirst. binding.wiki_pathdoes not resolve to a directory containing.cogni-wiki/config.json— the binding is stale.
Parameters
| Parameter | Required | Description |
|---|---|---|
--knowledge-slug |
Yes | Slug of the bound knowledge base. |
--project-path |
Yes | Absolute path to the project directory (produced by knowledge-plan). |
--knowledge-root |
No | Override the default knowledge-base directory. |
--sub-question-ids |
No | Comma-separated subset of sub-question ids to curate (e.g. sq-01,sq-03). Default: all from plan.json. Useful for resuming a partial curate. |
--dry-run |
No | Print the dispatch plan without running curators. |
--normalize-pdf-body |
No | Opt-in: thread NORMALIZE_PDF_BODY=true to every source-curator dispatch so the Phase-4 pdf-extract.py text-layer fallback stores a normalized body (NFKC-fold ligatures, map smart quotes/dashes to ASCII, rejoin hyphenated column-wrap breaks). Default off — the flag is not threaded, so the stored body / content_hash stay byte-identical. Applies only when pypdf is available and the Read tool cannot render the PDF. Enabling this on an existing base needs the affected raw-body PDF cache entries evicted first — see references/normalize-pdf-body-runbook.md. |
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 · -11 lines cda6ed435ba4
- 1mo ago First seen · 246 lines · 140 tokens per session scan A 1067fbbb42db
knowledge-curate is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 5,640 once invoked, about $0.0006 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…