kn-init

A session-start workflow for loading project documentation and current state in a Knowns project. It begins by checking the available project tools and then reads only the relevant documentation.

In plain words
What is it for?
Starting a session, checking whether the project is configured, listing and reading core documents, and focusing initialization on a task, feature, bug, or question.
Why use it?
It gives the agent the project context needed for later work instead of relying on guesses about the repository or its conventions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/knowns-dev/knowns/kn-init
Any agent
npx skills add knowns-dev/knowns --skill kn-init
Clone the repo
git clone --depth 1 https://github.com/knowns-dev/knowns

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01375
Opus 5 $0.00012 $0.00687
Sonnet 5 $0.00005 $0.00275
Haiku 4.5 $0.00002 $0.00137

Measured 3d ago against content hash cebeb490d35d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

internal/instructions/skills/kn-init/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 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 initial first when available; it is the runtime bootstrap
  • Use help("tool.*") or help("workflow.*") when an action schema or workflow route is not visible
  • Prefer project docs over guessing from code structure
  • If README, ARCHITECTURE, or CONVENTIONS do 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. A project that sets settings.defaultTaskIdPrefix generates IDs like KN-4F7Q2M; without it they look 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:

Read the full file on GitHub · 146 lines

Changes

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.

  1. 3d ago First seen · 146 lines · 23 tokens per session scan A cebeb490d35d

Subscribe to this mod's changes

kn-init is a skill published in the GitHub repository knowns-dev/knowns (241 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,375 once invoked, about $0.0001 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.

Related

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.

higress-group/higress · 53 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

data-artist

Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.

foryourhealth111-pixel/Vibe-Skills · 28 tokens

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens

deslop

Remove AI-generated code slop from a branch: unnecessary comments, redundant defensive checks, boilerplate, style drift, and type casts. Use for cleanup of AI-written code, not for broad code review, security audit, TDD, or final verification.

foryourhealth111-pixel/Vibe-Skills · 0 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens