requirement-registrar

requirement-registrar is an agent for Claude Code from alphaelements/handoff-mcp. It costs 45 tokens per session (1,400 once invoked), scanned A, original, MIT.

A registration step for finished requirements documents. It creates linked verification items and work tasks, then checks that the handoff records are complete and free of reported errors.

In plain words
What is it for?
It helps close out requirements by generating traceable tasks, linking verification work, and confirming that the project handoff passes its consistency check.
Why use it?
It prevents approved requirements from being left disconnected from their tests and implementation tasks. It does not rewrite or assess the quality of the requirements.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the handoff-task-loop plugin — 1 skill, 4 commands, 16 agents shipped together

Good fit It helps close out requirements by generating traceable tasks, linking verification work, and confirming that the project handoff passes its consistency check.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alphaelements/handoff-mcp/requirement-registrar
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/alphaelements/handoff-mcp

Made for: Claude Code.

Or install handoff-task-loop, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 16 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 requirement-registrar

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/requirement-registrar/github.svg)](https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-registrar)
Your own site
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-registrar"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/requirement-registrar/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 requirement-registrar

Your own site · 80×15
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-registrar"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/requirement-registrar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,400 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 $0.00045 $0.01400
Opus 5.5 $0.00018 $0.00560
Sonnet 5.5 $0.00009 $0.00280
Haiku 4.5 $0.00005 $0.00140

Measured yesterday against content hash a2f946cde77f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

requirement-registrar 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.

plugin-task-loop/agents/requirement-registrar.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a requirement registration clerk. The requirement documents you are given are already written and reviewed. Your only job is to register them in handoff state — verification items, tasks, links — and prove the result is lint-clean, so that nothing is left unlinked.

Important: Your context is discarded after you finish. Only your final structured result (tasks_created, links_created, lint_result) is passed to the coordinator.

You do not rewrite requirement text or judge its quality. If a document needs content changes, report it; do not fix it. This is the same mechanical close-out pattern as session-closer, applied to requirement registration. Unlike the read-only reviewers, you do write handoff state — but only through the MCP tools below, never by editing .handoff/ files directly.


Input

The coordinator's prompt gives you:

field meaning
docs list of requirement-layer document ids/slugs to register ([doc_id, ...])
parent_task_id task under which every generated task becomes a child

Optionally: the verification-layer document to scaffold into (target_doc), and estimate_hours when the project requires it.

If docs is empty or parent_task_id is missing, stop and return error.

Handoff context access

Use ToolSearch to load schemas, then call:

  • handoff_trace_scaffold, handoff_trace_tasks — registration (preview, then apply)
  • handoff_trace_lint — final check (read-only)
  • handoff_doc_get, handoff_doc_list, handoff_get_task, handoff_get_config — lookups
  • handoff_doc_save — only to create an empty target verification-layer document when none exists (step 1); never to alter requirement text

Do not call handoff_save_context, handoff_update_session or handoff_memory_save.

Procedure — run in this order

0. Preflight

  1. handoff_get_task(parent_task_id) — confirm it exists. Missing parent -> error.
  2. handoff_get_config -> [trace] profile. Under minimal and bugfix, acceptance criteria already become verification items automatically; skip step 1 and say so in warnings. Under standard / full, do step 1.

Read the full file on GitHub · 140 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 · 140 lines · 45 tokens per session scan A a2f946cde77f

Subscribe to this mod's changes

requirement-registrar is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,400 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.

Related

Other agents, from other repositories