handoff-execute

handoff-execute is a skill for Claude Code from allemaar/open-skills. It costs 129 tokens per session (5,028 once invoked), scanned A, original, Apache-2.0.

A command that carries out a handoff brief in a fresh agent session. It reads the brief's required sources before planning, follows its steps, checks the result, and records lessons learned.

In plain words
What is it for?
Use it when given a handoff brief from another session or agent, especially when the task requires source reading, a verified outcome, and a follow-up record of what was learned.
Why use it?
It turns a handoff into an executable task instead of leaving the new agent to guess what the previous session meant. Source and outcome checks help detect missing context or incomplete work.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the open-skills plugin — 58 skills shipped together

Good fit Use it when given a handoff brief from another session or agent, especially when the task requires source reading, a verified outcome, and a follow-up record of what was learned.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/allemaar/open-skills/handoff-execute
Install

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.

Any agent
npx skills add allemaar/open-skills --skill handoff-execute
Clone the repo
git clone --depth 1 https://github.com/allemaar/open-skills

Made for: Claude Code.

Or install open-skills, the plugin that ships this one along with the rest of its 58 skills.

Wrote 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.

agentmods badge for handoff-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/allemaar/open-skills/handoff-execute/github.svg)](https://agentmods.dev/skills/allemaar/open-skills/handoff-execute)
Your own site
<a href="https://agentmods.dev/skills/allemaar/open-skills/handoff-execute"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/handoff-execute/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.

agentmods 80×15 button for handoff-execute

Your own site · 80×15
<a href="https://agentmods.dev/skills/allemaar/open-skills/handoff-execute"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/handoff-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 168
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.05028
Opus 5 $0.00064 $0.02514
Sonnet 5 $0.00026 $0.01006
Haiku 4.5 $0.00013 $0.00503

Measured 10d ago against content hash 45f88905d1d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

handoff-execute 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.

skills/handoff-execute/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff-execute

Receive a handoff brief in a fresh agent session and execute it end-to-end with a source-ingestion gate before planning, source-cited plan steps, acceptance-verified output, and a ground-truth retro. This is the receiving-side counterpart to /handoff/handoff writes the brief, /handoff-execute enforces the discipline that turns the brief into ground-truth work.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Boundary

Use handoff-execute to consume a handoff brief produced by /handoff (YAML frontmatter type: handoff + YON body blocks). Do not use it for:

  • PLAN.md or implementation_plan.md — use /plan-execute (different schema, no @SOURCES block, no retro requirement).
  • A formal post-execution self-gate — use /verify (requires intent/plan/execution artifacts; checks for drift).
  • Independent outside-agent review of completed work — use /cold-review (reviews, doesn't execute).
  • Re-verifying one specific claim — use /double-check.

handoff-execute is the only skill that consumes a handoff brief and produces the canonical retro file.

Invocation

/handoff-execute "<absolute-path-to-brief>"

The brief path is required. Always quote the path — Windows vault paths may contain spaces.

Force flag/handoff-execute --force "<path>" downgrades the Phase 2 gate from ABORT to WARN, allowing execution to proceed even when one or more @SOURCES.required entries fail to read. Intended for async cases where the brief author isn't reachable to amend the brief; surfaced explicitly so it can't be invoked accidentally. The blocked retro is still written for audit.

Vault path dependency — Phase 5 writes the retro to $VAULT/Handoffs/{project}/retros/... (set $VAULT to your vault root). This path is inherited from /handoff. If $VAULT is unset or the host has no Obsidian vault, the cold agent must override the retro write target via the brief's output_location field, or the write will fail and the skill will fall back to chat-only retro emission with a @WRITE_FAILURE block (see Phase 5).

Read the full file on GitHub · 187 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 187 lines · 129 tokens per session scan A 45f88905d1d0

Subscribe to this mod's changes

handoff-execute is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 129 tokens to every session and 5,028 once invoked, about $0.0006 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.