kn-flow

kn-flow is a skill for Claude Code, Codex from knowns-dev/knowns. It costs 38 tokens per session (2,058 once invoked), scanned A, original, MIT.

A workflow coordinator for completing an approved specification or group of linked tasks from planning through implementation, review, and verification. It can order dependent work and optionally run safe parts in parallel.

In plain words
What is it for?
Use it to execute a full specification or task wave, schedule dependencies, create plans, coordinate implementation and review, and verify the combined result.
Why use it?
It provides one managed process for larger pieces of work instead of handling planning, coding, review, and checks separately.

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

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kn-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-flow.svg)](https://agentmods.dev/skills/knowns-dev/knowns/kn-flow)
Your own site
<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-flow"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,058 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 $0.00038 $0.02058
Opus 5 $0.00019 $0.01029
Sonnet 5 $0.00008 $0.00412
Haiku 4.5 $0.00004 $0.00206

Measured 3d ago against content hash 8caabec5514e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kn-flow 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-flow/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Flow Orchestration

Coordinate an approved spec, linked task set, or explicit task wave from planning through implementation, review, and verification.

Announce: "Using kn-flow for spec/task wave [ref]."

Core principle: APPROVED SPEC/TASK WAVE -> SCHEDULE -> PLAN -> IMPLEMENT -> REVIEW -> VERIFY.

When to Use

  • After /kn-spec approves a spec and the user wants the work completed end to end
  • When the user says "do all tasks", "complete this spec", "orchestrate sub-agents", "run the whole flow", or similar
  • When multiple linked tasks need dependency ordering, ownership boundaries, review, and combined verification

When NOT to Use

  • Draft specs or unresolved product questions -> use /kn-spec
  • A single task with an existing plan -> use /kn-implement <id>
  • Creating tasks only, without execution -> use /kn-plan --from @doc/<spec-path>
  • Tiny standalone work -> use /kn-plan --new "<summary>"

Inputs

  • Spec ref: @doc/<spec-path> preferred
  • Task IDs: one or more explicit tasks for a task wave
  • Optional: --sequential to force single-threaded execution
  • Optional: --plan-only to stop after plans and schedule

Startup

  1. Start with Knowns MCP initial.
  2. Read kn-plan, kn-implement, and kn-review before using their procedures.
  3. Read the spec or each explicit task.
  4. For every linked spec, read the complete canonical Locked Decisions section and keep its stable D-IDs as execution gates.
  5. Retrieve relevant accepted/current System Decisions with a feature/task query, sourceTypes:["decision"], status:"accepted", includeHistorical:false, and a bounded limit.
  6. Search first, then follow explicit refs and retrieve only relevant context.
  7. Do not manually edit Knowns-managed task or doc markdown.

Task Discovery

For a spec ref:

  1. Read the spec.
  2. List tasks linked to the spec.
  3. Read the spec's optional Task GenerationTask Prefix; when tasks must be generated, pass it as prefix on each create call without changing project config.
  4. Sort by order, then title. Generated IDs are identity, not workflow ordering.
  5. If no tasks exist, use /kn-plan --from @doc/<spec-path> behavior to preview tasks. Ask before creating tasks unless the user explicitly approved task creation.

Read the full file on GitHub · 194 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 · 194 lines · 38 tokens per session scan A 8caabec5514e

Subscribe to this mod's changes

kn-flow is a skill published in the GitHub repository knowns-dev/knowns (241 stars, last pushed 7d ago), licensed MIT. It adds 38 tokens to every session and 2,058 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.

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

flow-next-resolve-pr

Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.

gmickel/flow-next · 36 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

spk-mission-types

Explain Spec Kitty mission types, step contracts, action indices, and when to choose each mission workflow.

Priivacy-ai/spec-kitty · 26 tokens

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…

mindfold-ai/Trellis · 65 tokens

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…

Othmane-Khadri/YALC-the-GTM-operating-system · 123 tokens