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 agentmods add skills/knowns-dev/knowns/kn-implementnpx skills add knowns-dev/knowns --skill kn-implementgit clone --depth 1 https://github.com/knowns-dev/knownsWhat 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 | $0.00020 | $0.02871 |
| Opus 5 | $0.00010 | $0.01435 |
| Sonnet 5 | $0.00004 | $0.00574 |
| Haiku 4.5 | $0.00002 | $0.00287 |
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 2d 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 — 320 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.
- 2d 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 (241 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 2,871 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.
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.
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
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.
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.