Hanna: Command for Claude Code

.claude/commands/hanna-dispatch-next.md

hanna-dispatch-next is a command for Claude Code from JosephOIbrahim/Hanna. It costs 22 tokens per session (1,316 once invoked), scanned A, original, Apache-2.0.

A command that selects the next available work lane from `docs/ROADMAP.md` and dispatches it according to the project's decisions. A work lane is a defined stream of buildout tasks with dependencies and a status such as queued or done.

In plain words
What is it for?
Use it to find and start the next unblocked Hanna buildout lane, execute main-thread lanes, and verify their completion criteria.
Why use it?
It prevents starting tasks before their dependencies are complete and keeps progress aligned with the project's roadmap. It stops and reports the dependency state when no lane is ready.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

This is JosephOIbrahim/Hanna's own configuration. It tells Claude Code how to work on Hanna itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Hanna configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JosephOIbrahim/Hanna. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Hanna/main/.claude/commands/hanna-dispatch-next.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Hanna

Made for: Claude Code.

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 hanna-dispatch-next

README.md
[![agentmods](https://agentmods.dev/badge/commands/josephoibrahim/hanna/hanna-dispatch-next/github.svg)](https://agentmods.dev/commands/josephoibrahim/hanna/hanna-dispatch-next)
Your own site
<a href="https://agentmods.dev/commands/josephoibrahim/hanna/hanna-dispatch-next"><img src="https://agentmods.dev/badge/commands/josephoibrahim/hanna/hanna-dispatch-next/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 hanna-dispatch-next

Your own site · 80×15
<a href="https://agentmods.dev/commands/josephoibrahim/hanna/hanna-dispatch-next"><img src="https://agentmods.dev/badge/commands/josephoibrahim/hanna/hanna-dispatch-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,316 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 $0.00022 $0.01316
Opus 5 $0.00011 $0.00658
Sonnet 5 $0.00004 $0.00263
Haiku 4.5 $0.00002 $0.00132

Measured 9d ago against content hash bf656c7182a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hanna-dispatch-next 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 9d 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.

.claude/commands/hanna-dispatch-next.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hanna-dispatch-next

You are the harness for the Hanna buildout. This slash command advances the project by one lane per invocation, reading the single-source-of-truth status table in docs/ROADMAP.md §5 and dispatching the topmost unblocked lane per the MoE methodology ratified in docs/DECISIONS.md D002.

Protocol

  1. Read docs/ROADMAP.md entirely. Pay particular attention to §4 (per-lane spec) and §5 (lane status table).

  2. Identify the next lane. Scan §5 top-to-bottom. The next lane is the topmost row where Status == queued AND every dependency lane (named in the Unblocks columns of upstream rows, OR explicitly in §4 "Dependencies") has Status == done.

  3. If no lane is unblocked:

    • All lanes done → report "All lanes complete; Hanna buildout is finished. Run /hanna-buildout-status (future) or read NEXT.md for what's next."
    • Some queued but dependencies missing → report the dependency state and stop.
    • Stop without dispatching.
  4. If the lane is main-thread (per D002, substrate-decision class — currently L1 D008 propagation):

    • Execute the work directly per the §4 brief skeleton for that lane.
    • Verify completion criteria from §4.
    • Update §5 status table from queueddone and record the new commit SHA in the Last commit column.
    • Commit + push.
    • Report the lane's completion + the next unblocked lane.
  5. If the lane is MoE-eligible:

    • Read §4 for that lane's brief skeleton.
    • Dispatch the named expert(s) in parallel per D002 step 2, using the brief skeleton verbatim with any per-invocation specialization.
    • After all builder experts return, dispatch the Compliance Reviewer alone per D002 step 4.
    • Apply reviewer RECOMMENDED-CHANGES via Edit; re-dispatch any FAIL'd builder.
    • Verify completion criteria from §4 (pytest counts, grep results, brief artifacts).
    • Update §5 status table from queueddone and record the new commit SHA.
    • Commit (single commit per D002 step 6); push.
    • Report the lane's completion + the next unblocked lane.

Read the full file on GitHub · 92 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. 9d ago First seen · 92 lines · 22 tokens per session scan A bf656c7182a4

Subscribe to this mod's changes

hanna-dispatch-next is a command published in the GitHub repository JosephOIbrahim/Hanna (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,316 once invoked, about $0.0001 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.