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-specgit 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-spec)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-spec"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-spec/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-spec"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-spec.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 | $0.00017 | $0.03376 |
| Opus 5.5 | $0.00007 | $0.01350 |
| Sonnet 5.5 | $0.00003 | $0.00675 |
| Haiku 4.5 | $0.00002 | $0.00338 |
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 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 — 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-exploreto 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, andtasks.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 Linkssection 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.
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 a231d4e6f415
- 1mo ago First seen · 400 lines · 17 tokens per session scan A 9b94d381757a
kn-spec is a skill published in the GitHub repository knowns-dev/knowns (248 stars, last pushed 21d ago), licensed MIT. It adds 17 tokens to every session and 3,376 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:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
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:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.