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-researchnpx skills add cogni-work/insight-wave --skill knowledge-researchgit 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-research)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-research"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-research.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 | $0.00163 | $0.02943 |
| Opus 5 | $0.00081 | $0.01471 |
| Sonnet 5 | $0.00033 | $0.00589 |
| Haiku 4.5 | $0.00016 | $0.00294 |
Grade A, and why
knowledge-research 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Research
Research a topic and deposit the findings into a bound cogni-knowledge base in one command. This is the accumulation primitive — every run of this skill leaves the knowledge base denser than before, and the next run reads what previous runs filed.
This skill is a thin orchestrator over cogni-wiki:wiki-from-research (Mode A). The cogni-knowledge value-add is three things on top of wiki-from-research:
- Binding-aware wiki path resolution (no
--wiki-rootfrom the user — read it frombinding.json). - Lineage stamping (
derived_from_research: <slug>on every deposited page). - Binding append (record the project in
research_projects[]soknowledge-resumecan list it).
Read ${CLAUDE_PLUGIN_ROOT}/references/differentiation-thesis.md once at the start of a session to anchor on the accumulation thesis; read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md to remember the delegation boundary.
When to run
- User asks to research a topic INTO an existing knowledge base
- User wants the work to compound — second research on a related topic should read the first
- User explicitly invokes
/cogni-knowledge:knowledge-research
Never run when
- No
binding.jsonexists at the resolved knowledge root — offercogni-knowledge:knowledge-setupfirst. Do not silently create one; the binding is a deliberate commitment. - The user wants a one-shot research report with no persistence — point at
cogni-research:research-setupdirectly. cogni-knowledge is opinionated about wiki-first.
Parameters
| Parameter | Required | Description |
|---|---|---|
--knowledge-slug |
Yes | Slug of the bound knowledge base. Resolves to <cwd>/<slug>/ unless --knowledge-root overrides. |
--topic |
Yes (prompted) | Free-text research topic. Forwarded to cogni-wiki:wiki-from-research --topic. |
--knowledge-root |
No | Override the default knowledge-base directory. Defaults to <cwd>/<knowledge-slug>/. |
--research-overrides |
No | Comma-separated key=value hints forwarded to cogni-wiki:wiki-from-research --research-overrides (e.g. report_type=detailed,market=dach,target_words=5000). Default if absent: report_type=detailed. The user can still override every value in cogni-research:research-setup's interactive menu. |
--dry-run |
No | Print the resolved plan (binding, wiki path, dispatch) without running. |
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 · 184 lines · 163 tokens per session scan A be90d2c3b8da
knowledge-research is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 2,943 once invoked, about $0.0008 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…