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 skills add knowns-dev/knowns --skill kn-initgit 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-init)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-init"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-init/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/knowns-dev/knowns/kn-init"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01398 |
| Opus 5.5 | $0.00009 | $0.00559 |
| Sonnet 5.5 | $0.00005 | $0.00280 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
kn-init 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 20d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Initialization
Announce: "Using kn-init to initialize session."
Core principle: BOOTSTRAP WITH MCP INITIAL → DISCOVER WITH HELP → READ ONLY RELEVANT DOCS.
Inputs
- Optional user focus such as a task ID, feature area, bug, or question
- Current project root already opened in the agent session
Preflight
- Confirm this is a Knowns project
- Call MCP
initialfirst when available; it is the runtime bootstrap - Use
help("tool.*")orhelp("workflow.*")when an action schema or workflow route is not visible - Prefer project docs over guessing from code structure
- If
README,ARCHITECTURE, orCONVENTIONSdo not exist, choose the closest equivalents from the docs list - If a doc is large, read its TOC first and only open the relevant sections
Step 1: Runtime Bootstrap
mcp_knowns_initial({})
If the MCP client exposes the tool as initial rather than mcp_knowns_initial, call that tool. Summarize project state, tool domains, active timer, and any warnings.
Step 2: List Docs
mcp_knowns_docs({ "action": "list" })
Step 3: Read Core Docs
mcp_knowns_docs({ "action": "get", "path": "README", "smart": true })
For large docs, do not read the whole file. Use:
mcp_knowns_docs({ "action": "get", "path": "<path>", "toc": true })
mcp_knowns_docs({ "action": "get", "path": "<path>", "section": "<heading-or-number>" })
Step 4: Check Current State
mcp_knowns_tasks({ "action": "list", "status": "in-progress" })
mcp_knowns_tasks({ "action": "board" })
Note the shape of the Task IDs you get back. New IDs always carry a prefix,
from settings.defaultTaskIdPrefix or, when that is unset, derived from the
project name, so they look like KN-4F7Q2M. Older tasks may still have plain
IDs like 4f7q2m. Either way, pass the ID exactly as printed: the hyphen in
KN-4F7Q2M is part of the ID, not a task- reference prefix to strip.
The initial tool reports the active format. Over MCP you can override the
prefix per Task with tasks({ action: "create", prefix: "SPC" }); changing the
project default is a CLI or Settings action, not an MCP one:
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.
- 20d ago Changed · +1 lines 20390d980b2d
- 1mo ago First seen · 146 lines · 23 tokens per session scan A cebeb490d35d
kn-init is a skill published in the GitHub repository knowns-dev/knowns (248 stars, last pushed 21d ago), licensed MIT. It adds 23 tokens to every session and 1,398 once invoked, about $0.0001 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
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.