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-implementgit 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-implement)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-implement"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-implement/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-implement"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 317 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00020 | $0.03060 |
| Opus 5.5 | $0.00008 | $0.01224 |
| Sonnet 5.5 | $0.00004 | $0.00612 |
| Haiku 4.5 | $0.00002 | $0.00306 |
Grade A, and why
kn-implement 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 1mo 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementing a Task
Execute the implementation plan, track progress, and complete the task.
Announce: "Using kn-implement for task [ID]."
Core principle: CHECK AC ONLY AFTER WORK IS DONE.
Inputs
- Task ID
- Existing implementation plan
- Linked spec, docs, templates, and referenced tasks
Preflight
- Confirm a plan exists; if not, redirect to
/kn-plan <id>first unless user explicitly overrides - Read task notes and pending ACs before changing code
- Identify whether the task is standalone or linked to a spec
- If the request is to complete an approved spec or multiple linked tasks, route to
/kn-flow @doc/<spec-path>instead of implementing a single task in isolation - If linked to a spec, load the spec only as needed for requirements/AC context; do not pull a long task list into the prompt
- If linked to a spec, read every rule in its canonical
Locked Decisionssection before changing code. An unreadable rule or concrete conflict blocks implementation. - Retrieve relevant accepted/current System Decisions with
sourceTypes:["decision"],status:"accepted",includeHistorical:false, and a bounded task query. - Decide what verification is required: tests, lint, build, validation, manual checks
Step 1: Review Task
mcp_knowns_tasks({ "action": "get", "taskId": "$ARGUMENTS" })
If task status is "done" (reopening):
mcp_knowns_tasks({ "action": "update", "taskId": "$ARGUMENTS",
"status": "in-progress",
"appendNotes": "Reopened: <reason>"
})
mcp_knowns_time({ "action": "start", "taskId": "$ARGUMENTS" })
Verify: plan exists, timer running, which ACs pending.
Step 2: Check Templates
mcp_knowns_templates({ "action": "list" })
If template exists → use it to generate boilerplate.
Step 3: Work Through Plan
For each step:
- Do the work
- Check AC (only after done!)
- Append note
mcp_knowns_tasks({ "action": "update", "taskId": "$ARGUMENTS",
"checkAc": [1],
"appendNotes": "Done: brief description"
})
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.
- 1mo ago Changed · +7 lines 0ae54450a4a3
- 1mo ago First seen · 320 lines · 20 tokens per session scan A a1781ec12e43
kn-implement is a skill published in the GitHub repository knowns-dev/knowns (250 stars, last pushed 26d ago), licensed MIT. It adds 20 tokens to every session and 3,060 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-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.