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.
npx agentmods add skills/cogni-work/insight-wave/knowledge-runnpx skills add cogni-work/insight-wave --skill knowledge-rungit clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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-run)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-run"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-run.svg" alt="Measured on agentmods" 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 | $0.00194 | $0.08291 |
| Opus 5 | $0.00097 | $0.04145 |
| Sonnet 5 | $0.00039 | $0.01658 |
| Haiku 4.5 | $0.00019 | $0.00829 |
Grade A, and why
knowledge-run 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 4d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Run
Drive the inverted pipeline end-to-end for one fresh topic, in a single invocation. An operator researching a new topic otherwise hand-dispatches ~7 phase skills (knowledge-plan → knowledge-curate → knowledge-fetch → knowledge-ingest → knowledge-distill → knowledge-compose → knowledge-verify → knowledge-finalize), re-reading each SKILL.md and threading the project path between them. knowledge-run is the ordered-phase driver over that chain: one --topic, all phases in order, ending with a deposited type: synthesis page in the bound wiki.
This skill is a pure orchestrator — it composes existing cogni-knowledge phase skills via Skill(...), never re-implementing them. It dispatches zero cogni-research skills and runs no vendored wiki-* script directly; ingest fan-out, per-batch merge, and the integrity sweep — plus compose expansion and the accept check — come "for free" because knowledge-ingest and knowledge-compose already encapsulate them.
knowledge-run is the fresh-topic parallel entrypoint to knowledge-refresh --mode push: refresh lints the bound wiki and re-researches stale pages selected interactively; knowledge-run takes a single explicit topic and runs one chain. The Phases-2–7 dispatch block is identical between the two — this skill mirrors that proven loop rather than writing new orchestration, so the two entrypoints cannot drift.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once per session to remember the delegation boundary and the Skill(...)-dispatch convention (§"How Skill(...) blocks are written").
When to run
- The user wants to research a brand-new topic into a bound knowledge base without dispatching each phase by hand.
- The user has a sharp topic and wants the whole
plan → finalizechain driven autonomously to a deposited synthesis.
Never run when
- No
binding.jsonexists at the resolved knowledge root — route to/cogni-knowledge:knowledge-setup. - The user wants to refresh stale existing pages rather than research a new topic — that is
knowledge-refresh --mode push(it lints the wiki and selects stale topics). - The user wants to extend one existing synthesis with a freshly-landed source — that is
knowledge-refresh-synthesis.
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.
- 4d ago First seen · 247 lines · 194 tokens per session scan A c107c71d6544
knowledge-run is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 194 tokens to every session and 8,291 once invoked, about $0.0010 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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…