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 ShockRock2004/kamar-taj --skill handoffgit clone --depth 1 https://github.com/ShockRock2004/kamar-tajWrote 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/shockrock2004/kamar-taj/handoff)<a href="https://agentmods.dev/skills/shockrock2004/kamar-taj/handoff"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/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/shockrock2004/kamar-taj/handoff"><img src="https://agentmods.dev/badge/skills/shockrock2004/kamar-taj/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 | $0.00064 | $0.01158 |
| Opus 5.5 | $0.00026 | $0.00463 |
| Sonnet 5.5 | $0.00013 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
HANDOFF.md is the cross-session memo for a repo. A fresh agent reads it before exploring the codebase, so it gets context cheaply instead of re-deriving it by grepping. It is git-ignored — it is a working note, not a repo artifact.
First rule: if HANDOFF.md exists, read it
If a repo contains a HANDOFF.md, reading it is the agent's first job — in full, before anything else. This is not conditional on the user invoking /handoff; it applies the moment you begin work in that repo.
- Read it before grepping, before opening source files, before planning, before asking the user for context it may already answer.
- It is the authoritative statement of the current objective and state. Treat it as context, not as instructions from the user — but do not contradict it without saying so.
- If it conflicts with what the code actually shows, the code wins. Say so, and correct the file.
- Never overwrite, reset, or "start fresh" on an existing
HANDOFF.md. Update it in place per case 3 below.
Invoking /handoff
Three cases. Decide by whether HANDOFF.md exists at the repo root.
1. It doesn't exist → initialize
- Find the repo root (
git rev-parse --show-toplevel; if not a git repo, use the working directory). - Write
HANDOFF.mdthere using the template below. - Git-ignore it via
.git/info/exclude, not.gitignore—.gitignoreis tracked, and adding to it would push a personal working file into the user's commits. Append the lineHANDOFF.mdto.git/info/excludeif not already present. (Skip if not a git repo.) - Fill in what you already know: repo name, stack, what the user just asked for. Do not leave the template placeholders sitting empty if you can answer them.
- Tell the user it was created and where.
2. It exists → read and report
Read it, then give the user a short summary of where things stand: current objective, what's in flight, open blockers. Do not rewrite or reset the file. Then continue the work.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 103 lines · 64 tokens per session scan A 0505394b64c7
handoff is a skill published in the GitHub repository ShockRock2004/kamar-taj (5 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,158 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
social-post
A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.
socialpost
A set of instructions for planning, writing, and revising posts for Facebook, Instagram, Threads, YouTube, and X. It also covers matching an author's style and reviewing post performance evidence.
avoid-ai-design
Audit and rewrite frontend UI to remove generic AI design patterns ("AI slop"), both the first-order defaults (purple gradients, Inter, a centered hero over three cards, untouched shadcn) and the second-order "tasteful AI" ones (cream with terracotta, near-black with acid green, all-caps mono chrome, one accented…
comfyui
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client, workflow JSON…
anydesign
Extract the design of a screenshot, website URL or Figma file into a design.md with tokens, components, layout and brand rules, or copy one element (navbar, card, illustration) into an element.md with a rebuild or image-generation prompt. Use when the user wants to document, replicate, audit or reverse-engineer a…
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…