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 stark-ai-de/agent-skills --skill handoffgit clone --depth 1 https://github.com/stark-ai-de/agent-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/stark-ai-de/agent-skills/handoff)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/handoff"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-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/stark-ai-de/agent-skills/handoff"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-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 | $0.00056 | $0.00679 |
| Opus 5 | $0.00028 | $0.00340 |
| Sonnet 5 | $0.00011 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Goal
Create a compact continuation artifact that lets another agent resume the task without re-reading the entire thread or losing important decisions.
Trigger conditions
- The user asks for a handoff, checkpoint, resume note, or context summary.
- The current thread is long or close to compaction.
- Work must pause before validation, review, merge, or release.
When to use
- Use when another agent, thread, or future session must continue the same work.
- Use before compacting a long-running implementation or review thread.
When not to use
- Do not use for a final answer when the task is complete.
- Do not use to replace source files, issues, PR descriptions, or validation logs.
Inputs to inspect
- Latest user instruction, current objective, changed files, validation commands, failures, and blockers.
- Use
git status --shortandgit diff --statwhen working inside a repository.
Rules
- Reference files, diffs, PRs, issues, and reports by path or URL instead of duplicating content.
- Include only decisions, evidence, validation status, blockers, and next steps needed to continue.
- Separate confirmed facts from assumptions.
- Keep secrets out of the handoff.
Workflow
- Identify the objective and the latest user instruction.
- Summarize decisions and why they were made.
- List changed files or active work areas.
- Record commands run and their outcomes.
- Name blockers, risks, and missing approvals.
- End with the next concrete action.
Commands
Useful commands before writing:
git status --short
git diff --stat
git log --oneline -5
Safety rules
- Do not include tokens, credentials, or sensitive snippets.
- Do not imply validation passed unless it was run and succeeded.
- Do not bury approvals required for destructive or remote actions.
Assets
Use assets/handoff-template.md when the user wants a file-based handoff.
References
Read only when needed:
assets/handoff-template.md
Scripts
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.
- 10d ago First seen · 111 lines · 56 tokens per session scan A 5b20d981b90b
handoff is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 679 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
levelup-specify
Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.
change-publish
Promote accepted Change Decision Records (ChDRs) from drafts to project memory at .adlc/memory/chdr/, write OKF-style frontmatter, and regenerate the boot-facing .adlc/memory/chdr.md index that team-boot injects at session start. Use after /change-clarify has accepted ChDRs.
captain-recall
Use when the user asks WHY or WHAT-HAPPENED questions about this system — historical decisions, past incidents, why code/config is shaped a certain way, where something is deployed, who decided what, or the state of work in flight. Queries the tsubasa knowledge graph for cited answers.
captain-inject
Use when the user STATES A FACT about the system or tells the captain to remember/learn something — "update your knowledge", "remember this", "we dropped X for Y", "the outage was caused by Z", environment URLs, team contacts, deployment flows, tribal knowledge, corrections to what the Captain believes. Validates…
decision
Single entry point for all decision operations: capture, search, manage. Routes based on natural language intent.
capture-mcp-context
Record durable context from MCP servers and design or project tools into repository memory as proposed. Use when working with an MCP server like Figma, Linear, Jira, or Sentry, or after pulling design, ticket, or error context, to persist it for future sessions.