rust-agent-handoff

A handoff procedure for coordinating a team of Rust coding agents through YAML files. Each file records a task handoff in the shared `.local/handoff/` directory.

In plain words
What is it for?
Use it to create correctly named handoff files and coordinate Rust architecture, implementation, testing, performance, security, code review, continuous integration, and debugging tasks.
Why use it?
It provides a shared record when agents cannot see one another’s conversations, so design, coding, testing, performance, security, review, and debugging work can be passed between them.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/bug-ops/zeph/rust-agent-handoff
Any agent
npx skills add bug-ops/zeph --skill rust-agent-handoff
Clone the repo
git clone --depth 1 https://github.com/bug-ops/zeph

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00085 $0.03073
Opus 5 $0.00043 $0.01537
Sonnet 5 $0.00017 $0.00615
Haiku 4.5 $0.00009 $0.00307

Measured 2d ago against content hash 68af9381fc43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-agent-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 2d 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.

.zeph/skills/rust-agent-handoff/SKILL.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rust Agent Handoff Protocol

Subagents work in isolated context — they cannot see each other's conversations. This protocol enables structured communication through flat YAML files.

Directory Structure

.local/
└── handoff/
    ├── 2025-01-09T14-30-45-architect.yaml
    ├── 2025-01-09T15-00-00-developer.yaml
    └── ...

File Naming Convention

[!IMPORTANT] Filename MUST equal {id}.yaml - The handoff file name must exactly match the id field inside the YAML file.

Format: {id}.yaml where id = {timestamp}-{agent}

Example:

  • Handoff id: 2025-01-09T14-30-45-architect
  • Filename: 2025-01-09T14-30-45-architect.yaml
Agent Agent suffix in id
rust-architect architect
rust-developer developer
rust-testing-engineer testing
rust-performance-engineer performance
rust-security-maintenance security
rust-code-reviewer review
rust-cicd-devops cicd
rust-debugger debug
rust-critic critic

Communication Model

Parent Agent (or User)
    │
    ├── Task(rust-architect): "Design system"
    │       ↓
    │   rust-architect executes
    │       - reads handoff if path provided
    │       - does work
    │       - writes handoff file
    │       - RETURNS result with handoff path
    │       ↓
    ├── receives result, reads handoff path
    │
    ├── Task(rust-developer): "Implement. Handoff: <path>"
    │       ↓
    │   rust-developer executes
    │       ...

Key point: Subagents cannot call each other directly. They return results to parent, who orchestrates the next call.

On Startup

If handoff file path(s) provided in task description:

Single handoff:

cat <provided-path>

Multiple handoffs (when merging contexts):

cat <path1>
cat <path2>
# ...

Reading parent context (recommended):

After reading the provided handoff, read its parent reports to understand the full context chain:

Read the full file on GitHub · 367 lines

Files

What ships with it

9 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. 2d ago First seen · 367 lines · 85 tokens per session scan A 68af9381fc43

Subscribe to this mod's changes

rust-agent-handoff is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 3,073 once invoked, about $0.0004 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.