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 krzysztofsurdy/code-virtuoso --skill handoffgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/handoff)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/handoff"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/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/krzysztofsurdy/code-virtuoso/handoff"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/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 | $0.00051 | $0.01306 |
| Opus 5.5 | $0.00020 | $0.00522 |
| Sonnet 5.5 | $0.00010 | $0.00261 |
| Haiku 4.5 | $0.00005 | $0.00131 |
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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
A new session starts with no memory. Whatever you learned, tried, and decided is gone unless it is written down. A handoff note is the shortest document that lets the next reader continue at the exact next step instead of re-reading the codebase and repeating dead ends. Write it from facts you checked, not from memory of what you meant to do.
Write a handoff
- Capture state from the repo, not from recall. Run
git status,git branch --show-current,git log --oneline <base>..HEAD, and the test command. Uncommitted work is the main loss risk, so commit it as a WIP commit if the user agrees, or list the files. - Fill the template below. Leave a section out only if it is truly empty, and say "none" so the reader knows you did not forget it.
- Make the next step exact. One action the reader can start in the first minute: a command to run, a file and function to open. "Continue the refactor" is not a next step.
- Record dead ends. What you tried and why it failed is the most expensive thing to rediscover. Include the error text or the reason.
- Save it (see below) and tell the user the path.
Keep it to one screen, about 40 lines. Link to files, commits, tickets, and PRs instead of pasting their content. If a section runs long, the detail belongs in the code, a commit message, or a ticket.
Template
# Handoff: <short title>
Date: <YYYY-MM-DD> Branch: <branch> Base: <commit or PR>
## Goal
<One or two sentences: what is being built or fixed, and why. Link the ticket.>
## Current state
<Where things stand now. Passing or failing, what works, what is half done. Uncommitted files.>
## Done
- <sha> <what it did>
## Tried and failed
- <approach>: <why it did not work, error text or evidence>
## Open questions
- <question>: <who can answer, what depends on it>
## Next step
<The single first action, with the exact command or file.>
## Files and commands
- `<path>`: <why it matters>
- `<command>`: <what it does>
## Verify
<How to confirm the work is correct: the commands and the expected result.>
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 · 97 lines · 51 tokens per session scan A ccfaa296a1bb
handoff is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,306 once invoked, about $0.0002 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 2026-10-22.
Other skills, from other repositories
setup-pre-commit
A setup for Husky pre-commit checks in a JavaScript or TypeScript repository. A pre-commit hook runs automatically before a Git commit and can format staged files, check types, and run tests.
implement-spec
A coding workflow that implements a written specification through a set of linked tickets. It creates a branch and draft pull request, assigns independent work to separate agents, combines their changes, and prepares the result for review.
git-guardrails-claude-code
A Claude Code setup that blocks selected destructive Git commands before they run. Git is a tool for tracking code changes; the blocked commands include pushing, deleting branches, discarding changes, and hard resets.
meanest-editor
Roast a pitch or press release with the eye of a veteran PR director. Honest, sharp, constructive — never cruel for its own sake.
headline-generator
Generate headline candidates from a story's raw facts: news-style headlines, press-release headlines, and pitch subject lines. A pure generation skill — it finds the charge in the facts, then runs ten proven moves (consequence, picture, number-as-hero, two-beat turn, naming, reader's-own-story, open question, voice…
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…