A workflow for writing a self-contained handoff between two repositories that do not share project knowledge. It supports a brief from one side and an API contract from the other.

Preparing a frontend-to-backend brief, answering one with a backend-to-frontend contract, and passing feature context between separate codebases.

It carries the requirements or finished interface across repository boundaries so the receiving team can work without access to the original repository's context.

kn-handoff — Skill for Claude Code and Codex by knowns-dev: A workflow for writing a self-contained handoff between two…

Install

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.

agentmods

npx agentmods add skills/knowns-dev/knowns/kn-handoff

Any agent

npx skills add knowns-dev/knowns --skill kn-handoff

Clone the repo

git clone --depth 1 https://github.com/knowns-dev/knowns

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-handoff.svg)](https://agentmods.dev/skills/knowns-dev/knowns/kn-handoff)

Your own site

<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="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00018	$0.01253
Sonnet 5	$0.00007	$0.00501
Haiku 4.5	$0.00004	$0.00251

Measured 6d ago against content hash e726e8d3433d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

internal/instructions/skills/kn-handoff/SKILL.md · 191 lines

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-spec and /kn-flow directly
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) or contract (this repo -> the repo that sent a brief)
handoff-id: reuse the existing id when replying; generate hof-<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

Read the full file on GitHub · 191 lines

Changes

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.

6d ago First seen · 191 lines · 37 tokens per session scan A e726e8d3433d

Subscribe to this mod's changes

kn-handoff is a skill published in the GitHub repository knowns-dev/knowns (242 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 2,506 once invoked, about $0.0002 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.

Project management ai ai-agents ai-native ai-workflow cli context-management

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.

higress-group/higress · 53 tokens

trellis-brainstorm

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…

mindfold-ai/Trellis · 65 tokens

architecture-reviewer

Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before…

shep-ai/shep · 80 tokens

hermesoffice-decks

Produce presentations in HermesOffice Slides — the plandeck/generatedeck pipeline, native element editing, and the templates/decks style specs (modern, elegant, professional, keynote-speaker, minimal, tech-dark, investor-pitch, workshop). Load for any request that creates or restyles a deck.

criptogus/HermesOffice · 68 tokens

fullenrich-content-engagers

Use when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into a CSV", "enrich this CSV of leads", "FullEnrich content engagers", or any variant indicating they want to convert a list of leads — either…

Othmane-Khadri/YALC-the-GTM-operating-system · 123 tokens

enrich-with-signals

Pull PredictLeads buying-intent signals (jobs, news, funding, tech, leadership changes) for a result set of companies and write them back into the local cache. Use when the user says 'enrich these companies with signals', 'add buying signals to this list', 'pull intent data for [domain]', 'check signals for these…

Othmane-Khadri/YALC-the-GTM-operating-system · 105 tokens