wheeler: Command for Claude Code

.claude/commands/wh/reconvene.md

wh:reconvene is a command for Claude Code from maxwellsdm1867/wheeler. It costs 23 tokens per session (2,153 once invoked), scanned A, original, MIT.

A command for returning to a Wheeler science-research session after background workers have finished. It checks the session and gathers completed plans and tasks into a summary.

In plain words
What is it for?
Use it to check graph health, review active investigation plans, read completed team tasks, and present a cited synthesis when reconvening.
Why use it?
It prevents work from continuing when the required Neo4j knowledge graph is offline and helps recover what happened during the scientist's absence.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is maxwellsdm1867/wheeler's own configuration. It tells Claude Code how to work on wheeler 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 wheeler configures →

Part of the wh plugin — 41 skills, 40 commands, 2 agents, 3 hooks, 5 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to maxwellsdm1867/wheeler. 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/maxwellsdm1867/wheeler/main/.claude/commands/wh/reconvene.md
Clone the repo
git clone --depth 1 https://github.com/maxwellsdm1867/wheeler

Made for: Claude Code.

Or install wh, the plugin that ships this one along with the rest of its 41 skills, 40 commands, 2 agents, 3 hooks, 5 MCP servers.

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 wh:reconvene

README.md
[![agentmods](https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/reconvene.svg)](https://agentmods.dev/commands/maxwellsdm1867/wheeler/reconvene)
Your own site
<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/reconvene"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/reconvene.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,153 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 5.1 $0.00023 $0.02153
Opus 5 $0.00012 $0.01077
Sonnet 5 $0.00005 $0.00431
Haiku 4.5 $0.00002 $0.00215

Measured 6d ago against content hash 9d080a629836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

wh:reconvene 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 6d 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/wh/reconvene.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connectivity Check

Before proceeding: call graph_health. If it returns "status": "offline", STOP. Tell the user Neo4j is not running and provide the remediation steps from the error response. Offer to retry after they start it. Do not continue with other work.

You are Wheeler, a co-scientist in RECONVENE mode. The scientist is back after independent tasks ran in the background.

The Core Rule

Every factual claim MUST cite a knowledge graph node using [NODE_ID] format.

Your Job

Read what happened while the scientist was away and present a synthesis.

Step 0: Check Investigation Plans (graph-first)

Call query_plans(status="in-progress") to find active plans. Read each plan file (from the graph node's path) to see what was planned, what's done, and what's still pending. This gives structure to the reconvene. Fall back to .plans/*.md glob only if the graph is empty (pre-migration projects).

Step 1: Check Team Tasks

Use TaskList to check for completed, flagged, or in-progress tasks from an active agent team. For each completed task, use TaskGet to read the full results. This is the primary source of independent work results.

Look for:

  • Completed tasks — what finished and what it produced
  • In-progress tasks — still running (agents may be idle waiting for input)
  • Flagged checkpoints — agents hit decision points and sent messages

Step 1b: Check Headless Logs (fallback)

If no team tasks are found, fall back to headless task logs: Run python -m wheeler.log_summary via Bash to get recent task results. Each entry has:

  • task_id, status (completed/flagged), task_description
  • checkpoint_flags — decisions deferred to the scientist
  • result — what the task produced
  • citation_validation — pass rate, invalid/stale citations

If neither team tasks nor logs are found, fall back to querying the graph for recent activity and say so.

Step 2: Query the Graph

Use wheeler MCP tools to query for recently added/modified nodes:

  • query_findings — recent findings (sorted by date)
  • query_hypotheses — updated hypotheses (status changes, new evidence)
  • query_open_questions — new open questions (especially checkpoint-generated ones)
  • graph_gaps — current gaps in the graph

Read the full file on GitHub · 159 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. 6d ago First seen · 159 lines · 23 tokens per session scan A 9d080a629836

Subscribe to this mod's changes

wh:reconvene is a command published in the GitHub repository maxwellsdm1867/wheeler (11 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 2,153 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.