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/knowns-dev/knowns/kn-researchnpx skills add knowns-dev/knowns --skill kn-researchgit clone --depth 1 https://github.com/knowns-dev/knownsWrote 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/knowns-dev/knowns/kn-research)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-research"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-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 | $0.00033 | $0.01724 |
| Opus 5 | $0.00016 | $0.00862 |
| Sonnet 5 | $0.00007 | $0.00345 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
kn-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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researching the Codebase
Announce: "Using kn-research for [topic]."
Core principle: UNDERSTAND WHAT EXISTS BEFORE ADDING NEW CODE.
Research is read-only by default. Do not create or update tasks, docs, memories, decisions, or source files unless the user explicitly requests persistence or an approved parent workflow already authorizes it.
Inputs
- Topic, feature, API, error, file pattern, or task ID
- Suspected paths, symbols, packages, refs, or external facts to verify
- Optional: additional repository roots when the feature spans more than one repository
Multi-Repo Scope
A feature can span repositories that do not share a Knowns store, such as a frontend and a backend. When the user supplies additional repository roots, research all of them before drawing conclusions, and keep their boundaries explicit.
- Knowns search, retrieve, structural resolution, and code intelligence are scoped to the current project. For an additional root, use file and code search against that root directly.
- Additional roots are read-only. Never create or modify tasks, docs, memories, decisions, or source files outside the current project, even when the user authorizes persistence here.
- Prefix every file reference with its repository name, because the same relative path often exists on both sides:
knowns-web/src/features/orders/hooks/useRefund.ts:28
knowns-api/internal/services/refund_service.go:142
- Report conventions, constraints, and existing patterns per repository. Two repositories rarely share testing, validation, or naming rules, and assuming they do produces a plan that is wrong on one side.
- State which side owns each open question, so the finding can become a cross-repo handoff without further triage.
Search Order
Use the narrowest surface that can answer the question, then widen deliberately:
- Project docs, memories, and current decisions
- Structural relations from relevant specs/docs
- Related and completed tasks
- Existing code paths and implementations
- Adjacent tests, templates, and validation logic
- External sources only when the answer depends on current or upstream information
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.
- 5d ago First seen · 185 lines · 33 tokens per session scan A f5876e534760
kn-research is a skill published in the GitHub repository knowns-dev/knowns (242 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,724 once invoked, about $0.0002 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
agent-session-monitor
Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.
architecture-reviewer
Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before…
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
hermesoffice-decks
Produce presentations in HermesOffice Slides — the plandeck/generatedeck pipeline, native element editing, and the templates/decks style specs (modern, elegant, professional, keynote-speaker, minimal, tech-dark, investor-pitch, workshop). Load for any request that creates or restyles a deck.
fullenrich-content-engagers
Use when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into a CSV", "enrich this CSV of leads", "FullEnrich content engagers", or any variant indicating they want to convert a list of leads — either…
enrich-with-signals
Pull PredictLeads buying-intent signals (jobs, news, funding, tech, leadership changes) for a result set of companies and write them back into the local cache. Use when the user says 'enrich these companies with signals', 'add buying signals to this list', 'pull intent data for [domain]', 'check signals for these…