harness-handoff

harness-handoff is a command for Claude Code from kimsanguine/hplan. It costs 62 tokens per session (410 once invoked), scanned A, original, MIT.

A command that exports an approved Build Gate brief to Spec-Kit, Kiro, GStack, Claude Code, or all four. A Build Gate is a checkpoint deciding whether a product is ready to build.

In plain words
What is it for?
Use it to export a brief, create Spec-Kit or Kiro specification files, prepare GStack input, or add AGENTS.md and CLAUDE.md instructions for Claude Code.
Why use it?
It checks the approval evidence and tells you which files were created and where they must be placed. This reduces errors when moving a plan between development tools.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the hplan plugin — 8 skills, 11 commands, 4 agents shipped together

Good fit Use it to export a brief, create Spec-Kit or Kiro specification files, prepare GStack input, or add AGENTS.md and CLAUDE.md instructions for Claude Code.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kimsanguine/hplan/harness-handoff
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/kimsanguine/hplan

Made for: Claude Code.

Or install hplan, the plugin that ships this one along with the rest of its 8 skills, 11 commands, 4 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 harness-handoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-handoff/github.svg)](https://agentmods.dev/commands/kimsanguine/hplan/harness-handoff)
Your own site
<a href="https://agentmods.dev/commands/kimsanguine/hplan/harness-handoff"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-handoff/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 harness-handoff

Your own site · 80×15
<a href="https://agentmods.dev/commands/kimsanguine/hplan/harness-handoff"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 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 $0.00062 $0.00410
Opus 5 $0.00031 $0.00205
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 8d ago against content hash 64c2fbe0f888, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness-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 8d 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.

hplan/commands/harness-handoff.md · 33 lines

What it actually says

/harness-handoff

Instructions

You run the hplan multi-target handoff for: $ARGUMENTS

Step 1 — Verify Build Gate

Confirm harness/decisions.jsonl has a recent decision: "build" (or CONDITIONAL_GO) for this project AND harness/build-gate/checkpoint.json has status: "approved".

Step 2 — Locate the brief JSON

The brief must include at minimum: product_name, problem, icp, jtbd, cogs_ceiling, decision. Other fields fill gaps in generated artifacts.

Step 3 — Execute

python3 hplan/scripts/export_handoff.py <brief.json> --target <spec-kit|kiro|gstack|claude|all> --root .

Step 4 — Place outputs

Help the user move generated files from harness/exports/<target>/ to their actual project location (spec-kit specs/ at repo root, kiro .kiro/ at repo root, gstack /office-hours direct paste, claude AGENTS.md+CLAUDE.md at repo root).

Output Format

Return:

  1. Targets exported — list of files written per ecosystem
  2. NNN prefix used — for spec-kit auto-increment
  3. Next manual step — where to copy the generated files to make the downstream agent see them
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. 8d ago First seen · 33 lines · 62 tokens per session scan A 64c2fbe0f888

Subscribe to this mod's changes

harness-handoff is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 23d ago), licensed MIT. It adds 62 tokens to every session and 410 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.