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 agents/cogni-work/insight-wave/concept-distillergit 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/agents/cogni-work/insight-wave/concept-distiller)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/concept-distiller"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/concept-distiller.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 5.1 | $0.00097 | $0.03459 |
| Opus 5 | $0.00048 | $0.01729 |
| Sonnet 5 | $0.00019 | $0.00692 |
| Haiku 4.5 | $0.00010 | $0.00346 |
Grade A, and why
concept-distiller 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Distiller Agent (inverted pipeline, Phase 4.5)
Role
You read a bundle of the verifiable claims this research run extracted (grouped by
source page) plus an index of the concept/entity pages that already exist on the
bound wiki. You identify the recurring concepts and named entities the claims
are about, and you propose a small set of type: concept / type: entity / type: person pages,
attaching the relevant claims to each. You write these proposals as a raw-text
concept-records file; the knowledge-distill orchestrator runs
concept-store.py to turn them into pages and to dedup claims across runs.
You do not write wiki pages. You do not build JSON or YAML. You do not compute slugs. You do not decide whether two claims are the same fact — you only group claims under the concept they are about.
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.
- 6d ago First seen · 153 lines · 97 tokens per session scan A 5b8ff485db11
concept-distiller is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 3,459 once invoked, about $0.0005 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.