handoff

A handoff protocol for passing the current goal, status, evidence, risks, and next steps from one coding agent to another.

In plain words
What is it for?
Use it to create and validate JSON and Markdown handoff records, including commands run, artifacts, blockers, and any change-package reference.
Why use it?
It gives the next agent enough context to continue work without repeating the investigation or guessing what remains.

Agent

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 agents/itdojp/ae-framework/handoff
Clone the repo
git clone --depth 1 https://github.com/itdojp/ae-framework
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,964 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 $0.00000 $0.02964
Opus 5 $0.00000 $0.01482
Sonnet 5 $0.00000 $0.00593
Haiku 4.5 $0.00000 $0.00296

Measured yesterday against content hash 1b4f66b22c25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

docs/agents/handoff.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AE-HANDOFF Protocol

🌍 Language / 言語: English | 日本語


English

Overview

This document defines the minimum handoff protocol between agents. It does not replace the detailed summary in a Change Package. When a Change Package exists, reference it from the handoff instead of duplicating that detail.

Purpose

  • let the next agent decide immediately what to inspect, what to run, and which evidence to read
  • standardize PR and issue handoff comments so the handoff process does not depend on individual writing style

Standard outputs

  • JSON sidecar: artifacts/handoff/ae-handoff.json
  • Markdown sidecar: artifacts/handoff/ae-handoff.md
  • Schema: schema/ae-handoff.schema.json
  • Builder: pnpm run handoff:create -- --goal "<goal>"
  • Validator: pnpm run handoff:validate -- artifacts/handoff/ae-handoff.json schema/ae-handoff.schema.json

Required fields

  1. Goal
  2. Current status
  3. Next actions in execution order
  4. Commands run
  5. Artifacts
  6. Risks / rollback note when needed
  7. Blockers when present

Optional fields

  • Change Package reference
    • example: artifacts/change-package/summary.md
    • if no Change Package exists, record n/a in Markdown
    • in JSON, keep changePackageRef present and set it to null because the schema treats the field as required but nullable
  • Authority snapshot digest
    • pass a validated github-work-state/v1 file with --authority-snapshot <path>
    • the path must be repository-local and resolve to a regular non-symlink file
    • the builder copies only snapshotDigest into authoritySnapshotDigest and lists the snapshot as an artifact
    • a schema-invalid, digest-invalid, or wrong-head-check snapshot fails closed

JSON sidecar mapping

Markdown field JSON field
Goal goal
Current status currentStatus
Next actions nextActions[]
Commands run commandsRun[]
Artifacts artifacts[]
Risks / rollback note risksRollbackNote
Blockers blockers[]
Change Package changePackageRef
Authority snapshot authoritySnapshotDigest

Read the full file on GitHub · 287 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. yesterday First seen · 287 lines · 0 tokens per session scan A 1b4f66b22c25

Subscribe to this mod's changes

handoff is an agent published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,964 tokens. 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

playwright-test-generator

Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…

SigNoz/signoz · 0 tokens

playwright-test-healer

Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…

SigNoz/signoz · 0 tokens

playwright-test-planner

Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…

SigNoz/signoz · 0 tokens

codex

Production OpenAI-Codex-capable rootfs/initramfs.

the-void-ia/void-box · 0 tokens

claude

Production Claude-capable rootfs/initramfs.

the-void-ia/void-box · 0 tokens

doc-style

Markdown documentation prose — RFCs, ADRs, files under docs/, and READMEs — follows the same one-paragraph-per-line rule as commit messages. Write each paragraph on a single line; do not hard-wrap prose to a fixed column. The renderer reflows it to the reader's display width, whereas manual mid-paragraph line breaks…

the-void-ia/void-box · 0 tokens