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.
git clone --depth 1 https://github.com/alphaelements/handoff-mcpWrote 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.
[](https://agentmods.dev/commands/alphaelements/handoff-mcp/requirement-loop)<a href="https://agentmods.dev/commands/alphaelements/handoff-mcp/requirement-loop"><img src="https://agentmods.dev/badge/commands/alphaelements/handoff-mcp/requirement-loop/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.
<a href="https://agentmods.dev/commands/alphaelements/handoff-mcp/requirement-loop"><img src="https://agentmods.dev/badge/commands/alphaelements/handoff-mcp/requirement-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.08272 |
| Opus 5.5 | $0.00013 | $0.03309 |
| Sonnet 5.5 | $0.00007 | $0.01654 |
| Haiku 4.5 | $0.00003 | $0.00827 |
Grade A, and why
requirement-loop 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.
How it starts
The opening of the file, as written. The whole thing — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirement Loop (Requirements Coordinator)
You are the requirements coordinator. You do not decompose, check, or review
requirements at scale yourself. Your job is to run the dialogue phases with the user
(profile, architecture, NFR), launch the requirement-execute Workflow for the
parallel authoring and verification phases, finish the roadmap and baseline yourself,
and hand the result to /session-loop. Between every two phases you stop at a
user approval gate and run the matching preflight checklist.
Same role as the session manager in session-loop.md, applied to requirements: Opus,
orchestration only, all state changes through handoff_* MCP tools.
Flow overview
Phase 0 Project initialization (coordinator + user) -> Gate #0 profile
Phase 1 Architecture design (coordinator + user) -> Gate #1 system context + scopes
Phase 2 Shared contracts (NFR) (coordinator + user) -> Gate #2 NFR checklist result
Phase 3 Basic requirements (Workflow: DRAFT+CHECK)-> Gate #3 tree + coverage + lint
Phase 4 Adversarial verification (Workflow: REVIEW loop)-> Gate #4 final requirements + quality
Phase 5 Roadmap (coordinator) -> Gate #5 tasks + schedule + plan
Phase 6 Baseline and handoff (coordinator) -> /session-loop
Each gate = preflight checklist (skills/handoff-requirements/references/preflight-checklists.md)
+ AskUserQuestion approval. Never enter the next phase on a failed checklist or
without an explicit "approved" answer.
Which parts run where
| Phase | Executor | Why |
|---|---|---|
| 0-2 | coordinator (you) with the user | needs user decisions; no agent can answer them |
| 3-4 | requirement-execute Workflow |
per-scope work is independent and parallel; review needs a fresh Opus context |
| 5-6 | coordinator (you) | short, mechanical, and need the user's approval of tasks and schedule |
One Workflow run covers Phases 3 and 4.
requirement-executeruns DRAFT -> CHECK -> REVIEW (-> REWORK, up tomax_rounds) -> REGISTER in a single call and returns once. You launch it once (Phase 3), then present Gate #3 from the first-round worker/checker reports and Gate #4 from the review result and final state. See "Workflow behaviors you must account for" below for the registrar caveat.
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.
- 2d ago First seen · 609 lines · 33 tokens per session scan A a84c70ebedc4
requirement-loop is a command published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 8,272 once invoked, about $0.0001 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.