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-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-handoff"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 66 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00037 | $0.02506 |
| Opus 5.5 | $0.00015 | $0.01002 |
| Sonnet 5.5 | $0.00007 | $0.00501 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
kn-handoff 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Repo Handoff Documents
Produce the document that carries a feature between two repositories that do not share a Knowns store.
Announce: "Using kn-handoff to write the [brief|contract] for [handoff-id]."
Core principle: A HANDOFF DOC MUST BE READABLE IN A REPO THAT HAS NONE OF THIS REPO'S CONTEXT.
When to Use
- Frontend has shaped a feature and backend must now research and build the API
- Backend has finished the work and frontend must now integrate against a settled contract
- Any two-repo split where the receiving side opens a fresh session with no shared history
When NOT to Use
- Single-repo work -> use
/kn-specand/kn-flowdirectly - Passing context between tasks inside one repo -> use normal refs and
/kn-plan - Recording a durable architectural choice -> use a Decision, not a handoff
Inputs
- Mode:
brief(this repo -> other repo) orcontract(this repo -> the repo that sent a brief) handoff-id: reuse the existing id when replying; generatehof-<yyyy-mm-dd>-<slug>for a new one- Source material: the spec, research findings, and completed tasks in this repo
- For
contract: the brief being answered, so changes against it can be reported
Two Modes Are Different Documents
brief (FE -> BE) |
contract (BE -> FE) |
|
|---|---|---|
| Carries | questions and unconfirmed assumptions | settled, implemented fact |
| Authority | none, the receiver decides | authoritative for integration |
| Must not contain | receiver-side code, schema decisions, or claims stated as fact | unimplemented or speculative endpoints |
| Must contain | explicit open questions and risks | exact payloads, errors, and real examples |
Never blend the two. A brief that asserts backend design steals a decision that belongs to the backend developer. A contract that hedges leaves the frontend guessing.
Handoff Identity
Every handoff document opens with this block, written as plain text:
handoff-id: hof-2026-08-24-order-refund
direction: fe->be
version: 1
replies-to: (none | hof-2026-08-24-order-refund brief v1)
source-repo: knowns-web @ 3f9a1c2 ([email protected]:org/knowns-web.git)
target-repo: knowns-api
generated: 2026-08-24
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 First seen · 191 lines · 37 tokens per session scan A e726e8d3433d
kn-handoff is a skill published in the GitHub repository knowns-dev/knowns (249 stars, last pushed 23d ago), licensed MIT. It adds 37 tokens to every session and 2,506 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: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:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
alive-create
Scaffold a new walnut -- venture, experiment, person, life area, project.
alive-project
Regenerate now.json projections for all walnuts (mechanical, no approval needed).
expo-eas-submit
App Store Connect and Google Play Console upload flow with EAS Submit, metadata, build-artifact selection, review notes, and phased release. Triggers on eas submit, app store connect, google play, asc api key, service account, metadata, screenshot, phased release, review notes, testflight, internal testing, production…