A specification-writing skill for documenting a proposed software feature using a spec-driven development process. Spec-driven development means agreeing on requirements and design before planning or implementing the work.

Use it to explore decisions, write a feature specification, review it, and prepare it for approval. Specifications are stored using a dated folder and stable feature name.

It helps turn an idea into testable requirements and acceptance checks before coding begins. This makes important decisions visible and gives later implementation work a clear reference.

kn-spec — Skill for Claude Code and Codex by knowns-dev: A specification-writing skill for documenting a proposed software feature…

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-spec

Any agent

npx skills add knowns-dev/knowns --skill kn-spec

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-spec.svg)](https://agentmods.dev/skills/knowns-dev/knowns/kn-spec)

Your own site

<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-spec"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-spec.svg" alt="Measured on agentmods" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,372 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.

Model	Per session	Once invoked
Fable 5	$0.00017	$0.03372
Opus 5	$0.00009	$0.01686
Sonnet 5	$0.00003	$0.00674
Haiku 4.5	$0.00002	$0.00337

Measured 4d ago against content hash 9b94d381757a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kn-spec 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 4d 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-spec/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating a Spec Document

Create a specification document for a feature using SDD (Spec-Driven Development).

Announce: "Using kn-spec to create spec for [name]."

Core principle: EXPLORE DECISIONS -> SPEC -> REVIEW -> APPROVE -> THEN KN-FLOW OR TASK PLANNING.

Inputs

Feature name
User requirements, scenarios, constraints, and non-functional expectations
Related docs/tasks, if any
Optional: --skip-explore to jump straight to spec writing (for trivial features)
Optional: a cross-repo handoff document to shape the spec from

Spec Storage Convention

Create new specs under specs/<yyyy-mm-dd>/<slug> using today's date and a stable slug.
Keep the date in the folder, not the title: specs/2026-06-17/lsp-runtime-wrapper.
Use the exact spec path in all follow-up commands and task links.
Do not split a normal spec into requirements.md, design.md, and tasks.md. Keep one spec doc with sections; detailed execution belongs in Knowns Tasks.
If a spec already exists at specs/<slug>, keep using its existing path instead of moving it during normal spec work.

Spec Quality Rules

Requirements must be testable
ACs must be observable outcomes, not vague goals
Scenarios should cover happy path plus at least important edge cases
Open questions should stay explicit instead of being buried in prose
If background knowledge is too broad for the spec body, move it into a supporting doc and reference it
Keep task lists out of the spec body except for a short Task Links section after tasks are created

Spec Bypass Rule

Do not create a spec just because the user invoked kn-spec.

If the request is tiny, low ambiguity, and low risk, rule out a spec and recommend direct task creation:

/kn-plan --new "<short work summary>"

Use this bypass for narrow copy/docs/config tweaks, small bug fixes, and low-risk maintenance that does not change product contracts, architecture, data, auth, external integrations, or cross-module behavior.

Read the full file on GitHub · 400 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.

4d ago First seen · 400 lines · 17 tokens per session scan A 9b94d381757a

Subscribe to this mod's changes

kn-spec is a skill published in the GitHub repository knowns-dev/knowns (242 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 3,372 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.

Documents Planning Productivity ai ai-agents ai-native ai-workflow cli context-management

ospec

Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.

clawplays/ospec · 26 tokens

create-manifest

Create a Trellis migration manifest and matching docs-site changelogs for a target release by analyzing commits since the previous release. Use when preparing a patch, beta, rc, or minor release manifest.

mindfold-ai/Trellis · 44 tokens

shep-kit:research

Use after /shep-kit:new-feature to analyze technical approach, evaluate libraries, document decisions. Triggers include "research", "technical analysis", "evaluate options", "which library", or explicit /shep-kit:research invocation. Part of the Shep autonomous SDLC platform — https://shep.bot.

shep-ai/shep · 68 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

fullenrich-event-attendees

Use when the user says "enrich this LinkedIn event", "enrich attendees of this event", "enrich this attendees CSV", "scrape and enrich LinkedIn event {URL}", "FullEnrich event attendees", or any variant indicating they want to turn LinkedIn event attendees into an SDR-ready CSV with verified emails and mobile phones.…

Othmane-Khadri/YALC-the-GTM-operating-system · 0 tokens

qualify-leads

Run the GTM-OS 7-gate qualification pipeline over a batch of leads from a CSV, JSON, Notion DB, profile-visitors export, post-engagers export, or an existing SQLite result set. Writes per-lead pass/fail data back into SQLite and returns a result-set id you can hand to the campaign launcher. Use when the user says…

Othmane-Khadri/YALC-the-GTM-operating-system · 125 tokens