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 bartolli/kmd --skill handoffgit clone --depth 1 https://github.com/bartolli/kmdWrote 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/bartolli/kmd/handoff)<a href="https://agentmods.dev/skills/bartolli/kmd/handoff"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/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/bartolli/kmd/handoff"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00163 | $0.01347 |
| Opus 5.5 | $0.00065 | $0.00539 |
| Sonnet 5.5 | $0.00033 | $0.00269 |
| Haiku 4.5 | $0.00016 | $0.00135 |
Grade A, and why
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff — Close the Session from Corrected Truth
Why this exists
The primer is the first thing a cold session reads, and the session
that writes it is the one with the blind spots. So the primer is
written once, at the close, after a retro has surfaced what the
session did not claim — and the write is gated: retro-before-primer
denies it until a retro note postdates the scope's last edit. The
handoff is the operator's ceremony, never the agent's; the retro is
the grooming step that precedes it.
Prerequisites
WIKI_SCOPE: <scope>declared in the project instructions. If missing, suggest/wiki.- A retro note under
projects/<scope>/notes/retro-YYYY-MM-DD.mdwhoseupdatedis at or after the newest page under the scope'splan/,spec/,adr/, andintent/folders. Otherwise stop and run/retrofirst. - The scope's primer at
projects/<scope>/primer.md.
The protocol
Step 1 — Gate check
Read the newest retro note's updated and the newest updated under
the four working folders. If the retro is older, stop: /retro, then
back here. The pretool gate enforces this deterministically; checking
first avoids a denied write mid-ceremony.
Step 2 — Primer rewrite
Write the primer first — the gate compares the retro note against the scope's newest page, and the sweep and reconcile below move story clocks past it. The primer's reader is an agent: prime inlines it into the next
session's context. Write for that reader. Activate the signal-dense
register (/signal-dense) before drafting, and read
projects/<scope>/glossary.md first — every term the primer
uses is a canonical handle from there, typed the way the glossary
types it, never a synonym or a narrative paraphrase. Direct
predicates, no hedging, no register shifts.
Four sections, about 300 words, updated from the clock:
- Focus — three lines: what the scope is doing now and why.
- Next — the top three items, drawn from the Story Index and the
draft intents ordered by
sightings. A slice named where one is in progress. - Open — pointers to intents only. A question without an intent is filed as one first.
- Read order — three links.
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 · +2 lines 15bfcb0e013a
- 1mo ago Changed 2aa598444446
- 1mo ago First seen · 116 lines · 163 tokens per session scan A d22c815635c5
handoff is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 1,347 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…