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-refresh-synthesis)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-refresh-synthesis"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-refresh-synthesis/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-refresh-synthesis"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-refresh-synthesis.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 | $0.00167 | $0.04332 |
| Opus 5.5 | $0.00067 | $0.01733 |
| Sonnet 5.5 | $0.00033 | $0.00866 |
| Haiku 4.5 | $0.00017 | $0.00433 |
Grade A, and why
knowledge-refresh-synthesis 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Refresh Synthesis
Update an existing synthesis when a fresh source lands in the base, without re-deriving it from scratch. This is the dominant compounding case: a new source supersedes or extends a prior synthesis, and you want to fold it in — adding to the prior evidence base, never replacing it.
The base already detects this: synthesis-impact.py (run at knowledge-ingest-source
time) flags affected syntheses into binding.json::refresh_candidates[]. What was
missing is a first-class path to act on a candidate. Doing it by hand means ~10
error-prone steps stitched across knowledge-ingest-source, knowledge-compose,
knowledge-verify, and knowledge-finalize. The only existing one-shot route —
knowledge-refresh push-mode — routes the topic into a full Phase-1 plan re-run
whose knowledge-compose --source wiki re-derives the ingest-manifest via
wiki-grounding, which under-maps (a real run mapped only 21 of 35 original sources),
thinning the existing synthesis instead of extending it.
This skill is the targeted, manifest-unioning, single-synthesis orchestrator that
closes that gap. It unions the new source into the synthesis's existing project
manifest (ingest-manifest.json::ingested[]) — the new source is mapped in and added
to the prior set, never replacing it — then composes the existing phase skills via
Skill(...), never re-implementing them.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once per session to
remember the delegation boundary and the Skill(...)-dispatch convention.
When to run
- A new source has landed and
binding.json::refresh_candidates[]flags a synthesis it affects - The user wants to extend an existing synthesis from that source, not re-research the topic
- The user wants to resolve a refresh candidate without the wiki-grounding under-mapping that thins the page
Never run when
- No
binding.jsonexists at the resolved knowledge root — route to/cogni-knowledge:knowledge-setup - The binding has zero
refresh_candidates[](or noneopen) — there is nothing to refresh; suggestknowledge-refresh --mode pushfor time-based staleness instead - The targeted synthesis page has no
derived_from_researchfrontmatter (it was not deposited by the inverted pipeline, so there is no project manifest to union into) — abort with the message in Step 2 and suggestknowledge-refresh --mode pushto re-research the topic as a fresh project
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 First seen · 277 lines · 167 tokens per session scan A 6ed25c6346b8
knowledge-refresh-synthesis is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 4,332 once invoked, about $0.0007 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…