Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add int2t05/engineering-skills/plugin install engineering-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/int2t05/engineering-skills/handoff)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/handoff"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/handoff.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00655 |
| Opus 5 | $0.00024 | $0.00328 |
| Sonnet 5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
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 5d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a handoff brief summarizing the current conversation so a fresh agent can continue the work immediately. The brief is the only context the next session starts with — make it sufficient.
When to use
- The current session is ending and another agent (or a future you) will continue the work.
- Switching between foreground and background agents mid-task.
Not for: continuing work in the same session — just keep going; summarizing work that's already captured in specs/plans/ADRs — reference those by path instead.
Steps
- Summarize context and decisions. Capture the goal, what was decided and why, what was tried and rejected, and the current state. Don't restate what's already in artifacts — reference specs, plans, ADRs, issues, commits, and diffs by path or URL.
- List concrete next steps. Numbered, each independently actionable, starting from exactly where the work stopped.
- Suggest skills. Add a "Suggested skills" section naming the skills the next agent should invoke (e.g.
tdd,code-review). - Redact sensitive information. API keys, passwords, and PII must not appear in the brief — it may become a background agent's prompt or a shared file.
- Tailor to the next focus. If the user passed an argument describing what the next session is for, weight the brief toward that focus.
- Deliver. Save the brief to the OS temporary directory (not the current workspace), or launch a background agent seeded with it:
claude --bg --name "<descriptive name>" "<brief>". Always pass--namewith a descriptive title (e.g."Fix login bug") — it sets the display name in the job list, session picker, and terminal title. The launched agent starts in the current working directory and returns immediately; manage it withclaude agents.
Verify
- A fresh agent given only the brief could continue the work without asking "what's the state?"
- Next steps are concrete and start from where work stopped
- No content duplicated from existing artifacts (referenced by path/URL instead)
- No secrets, tokens, or PII in the brief
- Brief saved to the temp dir, or a named background agent launched with it
What ships with it
2 files 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.
- 5d ago First seen · 39 lines · 49 tokens per session scan A 806c1fb4d838
handoff is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 655 once invoked, about $0.0002 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
incident-response
Protocolo de respuesta ante incidentes en produccion: triaje, mitigacion, causa raiz y postmortem. Usar ante caidas, errores criticos, incidentes de seguridad o degradacion de servicio.
pr-workflow
Crear pull requests completas con descripcion, labels y reviewers.
compliance-check
Usar para verificar cumplimiento RGPD, NIS2 y CRA. También: verificar RGPD, cumplimiento normativo, NIS2, CRA, Cyber Resilience Act, protección de datos, regulación europea.
threat-model
Usar para modelar amenazas con metodología STRIDE. También: análisis de amenazas, STRIDE, superficie de ataque, vectores de ataque, modelado de amenazas.
sbom-generate
Usar para generar Software Bill of Materials para cumplimiento del CRA. También: Software Bill of Materials, inventario de componentes, CycloneDX, SPDX, cadena de suministro.
memory
This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the alfred-memory MCP server. Use it to call the namespaced MCP tools instead of inventing history.