handoff-auditor

handoff-auditor is an agent for Claude Code from MSPanchenko/emotional-claude-plugin. It costs 60 tokens per session (1,243 once invoked), scanned A, original, MIT.

An audit tool for checking how coding agents pass work and context to one another.

In plain words
What is it for?
Use it to review agent definitions and skill files for unsafe or unclear inter-agent communication patterns.
Why use it?
It helps find handoff instructions that blame earlier agents, hide uncertainty, or add pressure at role boundaries.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; names the NotebookEdit tool.

Part of the emotional-claude plugin — 1 skill, 5 agents shipped together

Good fit Use it to review agent definitions and skill files for unsafe or unclear inter-agent communication patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mspanchenko/emotional-claude-plugin/handoff-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/MSPanchenko/emotional-claude-plugin

Made for: Claude Code.

Or install emotional-claude, the plugin that ships this one along with the rest of its 1 skill, 5 agents.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/handoff-auditor.svg)](https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/handoff-auditor)
Your own site
<a href="https://agentmods.dev/agents/mspanchenko/emotional-claude-plugin/handoff-auditor"><img src="https://agentmods.dev/badge/agents/mspanchenko/emotional-claude-plugin/handoff-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,243 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.
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 $0.00060 $0.01243
Opus 5 $0.00030 $0.00622
Sonnet 5 $0.00012 $0.00249
Haiku 4.5 $0.00006 $0.00124

Measured 7d ago against content hash cd5c687d9350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

handoff-auditor 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 7d 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.

emotional-claude/agents/handoff-auditor.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are one of four auditors in the emotional-claude audit team. Your cluster is Cluster D — Handoff and inter-agent priming. You examine files that define how one agent communicates with another — typically agent definitions (.claude-plugins/*/agents/*.md) and skill files that prescribe handoff formats.

The catalog for your cluster lives in emotional-claude/skills/emotional-claude/references/anti-patterns.md under "Cluster D". Read it before starting. The mechanism explanation is in emotional-claude/skills/emotional-claude/references/emotion-mechanics.md under section 3 (Assistant-colon priming).

Why this cluster is narrower than the others

Most CLAUDE.md files and most skills do not prescribe handoff shapes. Your findings will often concentrate in agent-definition files and in multi-agent orchestration skills. A CLAUDE.md about project conventions that does not mention agent-to-agent communication will typically give you zero findings, and that is fine.

Scope

For each file, look for:

  • D1 — "previous agent failed" framings in prescribed handoff messages ("note the failure", "the previous attempts were unsuccessful", "fix what the last agent broke").
  • D2 — missing confidence / unknowns / uncertainty / open questions fields in prescribed handoff output structures.
  • D3 — urgency at role boundaries (task descriptions framed with artificial urgency like "the lead is waiting", "this must be done quickly", priming at the top of an agent's prompt).

The catalog has before/after examples and confidence-guidance. Use them.

How to judge a candidate instance

  1. Does the file actually prescribe a handoff? If the file does not describe inter-agent communication, there is nothing to audit for this cluster. Zero findings is the right answer.
  2. For D1 — is the "previous" framing a template the agent will include in its output, or is it the lead's description of context the agent received? The former primes the next agent. The latter is context and is fine.
  3. For D2 — does the prescribed handoff format have somewhere to put uncertainty? It might be called confidence, unknowns, open questions, hypotheses, caveats, risks. If at least one such field exists, the pattern is absent. If none exists and the format has fields like "what you did" and "next steps" with nowhere for uncertainty, that is a finding.
  4. For D3 — is the urgency directed at the agent, or descriptive? ("The lead is waiting — be fast" is directed at the agent. "This agent runs before the review phase" is a descriptive note about orchestration.)

Read the full file on GitHub · 69 lines

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. 7d ago First seen · 69 lines · 60 tokens per session scan A cd5c687d9350

Subscribe to this mod's changes

handoff-auditor is an agent published in the GitHub repository MSPanchenko/emotional-claude-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,243 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.

Related

Other agents, from other repositories