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-prefillnpx skills add cogni-work/insight-wave --skill knowledge-prefillgit 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-prefill)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-prefill"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-prefill.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 | $0.00116 | $0.02208 |
| Opus 5 | $0.00058 | $0.01104 |
| Sonnet 5 | $0.00023 | $0.00442 |
| Haiku 4.5 | $0.00012 | $0.00221 |
Grade A, and why
knowledge-prefill 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 today.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Prefill
Seed a bound knowledge base with curated foundation: true concept pages so canonical material like Porter's Five Forces, Jobs-to-be-Done, and MECE has a stable target slug from day one. This is the standalone analog of cogni-wiki:wiki-prefill, computed natively on the vendored prefill_foundations.py engine (resolved vendored-first via resolve_wiki_scripts()), so a Karpathy base is prefillable with no cogni-wiki plugin installed. It does not dispatch cogni-wiki:wiki-prefill.
Why this is a deliberate opt-in. knowledge-setup intentionally passes --skip-prefill-prompt to cogni-wiki:wiki-setup — a cogni-knowledge base has its own opinionated domain seeding (the first knowledge-plan → … → knowledge-finalize run seeds the base domain-specifically), and layering the generic canonical foundations on top would clutter it. knowledge-prefill is the native opt-in so a user who skipped foundations at setup time — or who wants the textbook concepts as stable link targets later — can add them without installing cogni-wiki.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once at the start of a session so you remember the wiki-engine boundary — cogni-knowledge runs the prefill on the vendored engine, it does not dispatch cogni-wiki:wiki-prefill.
When to run
- User explicitly asks to prefill, seed, or pre-load foundations / canonical concepts / consulting frameworks into the bound base
- A base set up with
--skip-prefill-prompt(the cogni-knowledge default) and the user now wants the canonical foundations as stable link targets - An existing base has accumulated duplicate pages for canonical material and the user wants to establish the foundation slugs
Never run when
- The target directory has no
.cogni-knowledge/binding.json— offerknowledge-setupinstead. - The user wants to add a single non-canonical concept — route that to
knowledge-ingest-source(one source into the base), or, for a full topic, to the inverted pipeline (knowledge-plan); foundations are reserved for textbook material that needs no per-base synthesis.
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.
- today Changed · -13 lines 59b4c6e7ac04
- 5d ago First seen · 156 lines · 116 tokens per session scan A 8b51e6695959
knowledge-prefill is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 116 tokens to every session and 2,208 once invoked, about $0.0006 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
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
extract
Builds the gauntlet knowledge base from AST extraction and AI enrichment. Use when initializing or refreshing codebase knowledge for challenges.
curate
Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not visible in code.