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-update)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-update"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-update/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-update"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-update.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 | $0.00161 | $0.03058 |
| Opus 5.5 | $0.00064 | $0.01223 |
| Sonnet 5.5 | $0.00032 | $0.00612 |
| Haiku 4.5 | $0.00016 | $0.00306 |
Grade A, and why
knowledge-update 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Update
Revise one page in a bound knowledge base because knowledge has changed, a contradiction was reported, or a new source refines a claim. This is the manual single-page curation half of the compounding loop — the inverted pipeline adds (ingest → distill → compose → finalize), and knowledge-update refines. Together they keep a Karpathy base live.
This is the standalone analog of cogni-wiki:wiki-update, computed natively against the bound wiki — it resolves the wiki root from .cogni-knowledge/binding.json and edits the page directly with the Edit tool, so a base is curatable with no cogni-wiki plugin installed. It does not dispatch cogni-wiki:wiki-update.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once at the start of a session so you remember the wiki-engine boundary — cogni-knowledge curates the page natively (the update logic is pure-LLM, Edit-driven; there is no engine script to resolve), it does not delegate to cogni-wiki:wiki-update.
When to run
- User explicitly asks to update, revise, retire, or fix a page in the bound base
knowledge-ingest-sourcedetected that a single source collides with an existing page and handed control here for diff-before-write (the intended endpoint for that cross-skill handoff)knowledge-lintreported a contradiction orclaim_driftthe user wants reconciled- User says "the base says X but actually Y — fix it"
Never run when
- The target directory has no
.cogni-knowledge/binding.json— offerknowledge-setupinstead. - The target page does not exist — offer
knowledge-ingest-sourceinstead. - The user wants to append a new claim with no source — stop and ask for the source first.
- The change is cosmetic only (a typo fix) — just
Editthe page directly and bump itsupdated:field; you do not need this skill's full discipline. - The target page has
foundation: truein frontmatter (seeded byknowledge-prefill) and the user did not pass--force. Foundations are terminal pages — canonical textbook concepts (Porter's Five Forces, Jobs-to-be-Done, MECE, …) whose authority derives from the upstream source URL, not per-base synthesis. Stop and surface the refusal verbatim:Page
{slug}is a foundation (canonical concept seeded byknowledge-prefill). Updates require--forceto preserve the terminal-page contract. Considerknowledge-ingest-sourcefor a base-specific page that links into [[{slug}]] instead.
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 · 165 lines · 161 tokens per session scan A a7669c4bdcee
knowledge-update is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 161 tokens to every session and 3,058 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn). Routes meetings to knowledge-meeting-ingest and short thoughts…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…