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-plan)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-plan"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-plan/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-plan"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-plan.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 | $0.00156 | $0.06065 |
| Opus 5.5 | $0.00062 | $0.02426 |
| Sonnet 5.5 | $0.00031 | $0.01213 |
| Haiku 4.5 | $0.00016 | $0.00607 |
Grade A, and why
knowledge-plan 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Plan
Phase 1 of the inverted pipeline (plan → curate → fetch → ingest → compose → verify → finalize). This skill decomposes a research topic into a structured plan that downstream phases (knowledge-curate, knowledge-fetch, …) consume.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md once at the start of a session to anchor on the phase boundaries and the contract.
When to run
- User wants to start a new research run on a topic against an existing bound knowledge base
- User explicitly invokes
/cogni-knowledge:knowledge-plan
Never run when
- No
binding.jsonexists at the resolved knowledge root — offerknowledge-setupfirst. Plan output lives in a fresh project directory under the bound knowledge root; without a binding there is no anchor. - The user wants the legacy research+ingest flow — that chain is archived under
_archive/(see_archive/README.md). The inverted pipeline is the only live path; if they truly want a one-shot report outside the knowledge base, point atcogni-research:research-setup.
Parameters
| Parameter | Required | Description |
|---|---|---|
--knowledge-slug |
Yes | Slug of the bound knowledge base. Resolves to cogni-knowledge/<slug>/ unless --knowledge-root overrides. |
--topic |
Yes (prompted) | Free-text research topic, e.g. "GDPR Article 30 records of processing". |
--knowledge-root |
No | Override the default knowledge-base directory. |
--market |
No | Market code. One of: dach, de, fr, it, pl, nl, es, us, uk, eu. Resolved in Step 0.5: explicit flag > binding research_defaults.market > dach. |
--output-language |
No | Two-letter code. Resolved in Step 0.5: explicit flag > binding research_defaults.output_language > the market's registry default_output_language > en. No longer a silent en default — a dach base now emits German without a flag. |
--prose-density |
No | standard (floor) or executive (BLUF + Pyramid ceiling). Resolved in Step 0.5: flag > binding research_defaults.prose_density > framing suggestion > executive. Threaded to wiki-composer/wiki-reviewer. |
--tone |
No | Writing tone (see ${CLAUDE_PLUGIN_ROOT}/references/writing-tones.md; one of 15). Resolved in Step 0.5: flag > binding research_defaults.tone > framing suggestion > objective. |
--citation-format |
No | All five render as requested; the split is a marker family, not a support level — ieee/chicago are numbered, apa/mla/harvard author-date (see ${CLAUDE_PLUGIN_ROOT}/references/citation-formats.md). Resolved in Step 0.5: flag > binding > framing suggestion > ieee. wikilink aliases to ieee. |
--target-words |
No | Positive int. Soft target (floor under standard, ceiling under executive). Resolved in Step 0.5: flag > binding > framing suggestion > 2000. Written into plan.json::target_words (which knowledge-compose/-reviewer read). |
--frame |
No | Force the optional Step 0 topic-framing pass even when the topic looks sharp. Forcing framing also engages the preliminary scoping scan (Step 0.4), so a sharp-topic user who wants scoping just passes --frame. |
--no-framing |
No | Skip Step 0 topic-framing entirely (also implied by --dry-run). |
--no-prelim-search |
No | Keep framing's sharpening but skip the preliminary scoping scan inside Step 0.4 — stays offline while still asking the framing questions. |
--sub-question-hints |
No | Pipe-separated list of sub-question seeds the user wants reflected, e.g. `"records of processing scope |
--dry-run |
No | Print the resolved plan + target paths without writing. Also skips Step 0 framing (non-interactive). |
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 b3829baed0be
- 1mo ago Changed · -16 lines 35799752a702
- 1mo ago First seen · 256 lines · 156 tokens per session scan A c873bfb818d6
knowledge-plan is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 156 tokens to every session and 6,065 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…