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-plangit 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-plan)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-plan"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-plan/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-plan"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-plan.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 | $0.00012 | $0.01855 |
| Opus 5.5 | $0.00005 | $0.00742 |
| Sonnet 5.5 | $0.00002 | $0.00371 |
| Haiku 4.5 | $0.00001 | $0.00186 |
Grade A, and why
kn-plan 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 25d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Work
Core principle: GATHER CONTEXT → PLAN → VALIDATE → WAIT FOR APPROVAL.
Modes
/kn-plan <task-id>— plan an existing task/kn-plan --new "<summary>"— create a bounded task, then plan it/kn-plan --from @doc/<spec-path>— preview and create tasks from an approved spec
If the user wants end-to-end execution of an approved spec or task wave, route to /kn-flow @doc/<spec-path>.
Shared Preflight
- Read the primary task or spec before searching adjacent context.
- Follow every explicit
@task-,@doc/, and@template/ref recursively. - Read a linked spec's complete
Locked Decisionssection and enumerate every D-ID. - Retrieve only relevant accepted/current System Decisions with bounded filters.
- Search docs, memories, related tasks, and templates only as needed.
- Stop on a missing primary source, unreadable rule, broken critical ref, or concrete Decision conflict.
Existing Task Mode
Announce: "Using kn-plan for task [ID]."
- Read the task and confirm it is not already done unless reopening is intended.
- Take ownership and start its timer. If another timer cannot be safely paused or replaced, surface that conflict rather than silently changing it.
- Gather bounded context from refs, related docs/tasks, code patterns, memories, templates, and relevant Decisions.
- Draft an outcome-oriented implementation plan.
- Save the plan to the task.
- Validate the task and run the plan-quality checks below.
- Present the plan and wait for explicit approval before implementation.
mcp_knowns_tasks({ "action": "get", "taskId": "<id>" })
mcp_knowns_tasks({ "action": "update", "taskId": "<id>",
"status": "in-progress", "assignee": "@me" })
mcp_knowns_time({ "action": "start", "taskId": "<id>" })
New Task Mode
Announce: "Using kn-plan to create and plan a new task."
Classify the summary:
- tiny/normal: create a concise task, then continue with Existing Task Mode
- high-risk or broadly ambiguous: recommend
/kn-specunless the user explicitly bypasses it
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.
- 25d ago Changed · +1 lines e9ec4214a066
- 1mo ago Changed · +31 lines 522a41640ea8
- 1mo ago First seen · 164 lines · 12 tokens per session scan A be7dca5bf8d3
kn-plan is a skill published in the GitHub repository knowns-dev/knowns (250 stars, last pushed 26d ago), licensed MIT. It adds 12 tokens to every session and 1,855 once invoked, about $0.0000 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-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: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: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.