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-refreshnpx skills add cogni-work/insight-wave --skill knowledge-refreshgit clone --depth 1 https://github.com/cogni-work/insight-waveWhat 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 | $0.00182 | $0.09046 |
| Opus 5 | $0.00091 | $0.04523 |
| Sonnet 5 | $0.00036 | $0.01809 |
| Haiku 4.5 | $0.00018 | $0.00905 |
Grade A, and why
knowledge-refresh 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Refresh
Close the self-healing loop for a bound cogni-knowledge base. Wiki pages age — the vendored lint_wiki.py flags stale_page (>365d) and stale_draft (>180d) findings, but lint alone doesn't bring fresh evidence. Push-mode lints the wiki, asks the user which stale topics they want fresh evidence on, then runs the inverted pipeline per selected topic: the seven-phase chain knowledge-plan → knowledge-curate → knowledge-fetch → knowledge-ingest → knowledge-distill (optional, fail-soft) → knowledge-compose → knowledge-verify → knowledge-finalize. Each topic ends with a freshly-composed, claim-verified type: synthesis page deposited into the bound wiki, and the distill step enriches the concept/entity web. An orthogonal opt-in --resweep flag re-verifies the bound wiki's cited claims against live source URLs.
This skill is a pure orchestrator — push-mode composes existing cogni-knowledge phase skills via Skill(...), never re-implementing them. Push-mode dispatches zero cogni-research skills — cogni-research is 0% of the runtime path.
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
- User wants to refresh stale pages in a bound knowledge base
- User wants the system to auto-research the stale topics (push-mode)
- User wants to re-verify the bound wiki's cited claims against live source URLs —
--resweep(opt-in)
Never run when
- No
binding.jsonexists at the resolved knowledge root — route to/cogni-knowledge:knowledge-setup - The bound wiki has zero stale pages AND
--mode push— there's nothing to push-refresh --mode push(or the default) was selected but the vendoredwiki-lintscript (lint_wiki.py) is missing from this install — abort with the standard missing-vendored-scripts message (Step 0 pre-flight)--resweepwas passed but the vendored wiki-claims-resweep scripts are missing from this install — abort with the standard missing-vendored-scripts message (Step 0 pre-flight)
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.
- 3d ago First seen · 297 lines · 182 tokens per session scan A d4dfa1fcbf9a
knowledge-refresh is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 182 tokens to every session and 9,046 once invoked, about $0.0009 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…