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 reidemeister94/development-skills --skill handoffgit clone --depth 1 https://github.com/reidemeister94/development-skillsWrote 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/reidemeister94/development-skills/handoff)<a href="https://agentmods.dev/skills/reidemeister94/development-skills/handoff"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/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/reidemeister94/development-skills/handoff"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/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 | $0.00029 | $0.00545 |
| Opus 5 | $0.00015 | $0.00272 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Create a standalone document that lets a person or agent continue the work in a new conversation. Follow the writing contract. Preserve the user’s request, useful discoveries, exact decisions, current state, relevant files, and the next action. Do not copy the conversation or raw logs.
Compute the path
Use the OS temp directory, never the repo:
${TMPDIR:-/tmp}/handoff-YYYY-MM-DD-HHMMSS-{slug}.md
{slug}= kebab-case topic, from$ARGUMENTSif passed, else inferred from the work.- Resolve
${TMPDIR:-/tmp}with Bash; macOS may not use/tmp.
Write
Write the absolute path. Keep the first three sections. Include the later sections only when they carry useful information.
# Handoff: {topic}
## What the user wants
[Explain the requested result and why it matters. Preserve exact wording only for decisions that the next conversation must not reinterpret.]
## Where things stand
[Explain what works, what is incomplete or broken, and the evidence. Give exact files, line numbers, and errors where they matter.]
## Next step
[`$ARGUMENTS` as a clear directive, or the next concrete action inferred from the current state.]
## Decisions that must survive
- [Decision and reason. Add a rejected alternative only when it helps prevent the same debate.]
## What the next agent needs to know
- [Constraint, project rule, hidden dependency, environment detail, or known trap.]
## Files and existing work
- `path/to/file.ext` — [what it contains and why it matters]
- Plan: `docs/plans/NNNN__...md` — [what it settles]
- Chronicle: `docs/chronicles/NNNN__...md` — [what it records]
- Other: [PRD, ADR, issue, pull request, commit, or URL]
## Questions still open
- [Question, why it matters, and who can answer it.]
## Useful skills
- `development-skills:<name>` — [when and why to use it]
Announce
Print HANDOFF WRITTEN: {full absolute path} followed by:
Read the handoff at: {full absolute path written above}
Then continue from the "Next step" section.
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.
- 9d ago First seen · 66 lines · 29 tokens per session scan A 726e5dbe21b5
handoff is a skill published in the GitHub repository reidemeister94/development-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 545 once invoked, about $0.0001 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.
Other skills, from other repositories
subagents-orchestration-guide
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
integration-e2e-testing
Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
recipe-review
Reviews completed implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved corrections.