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.
npx agentmods add commands/maxwellsdm1867/wheeler/resumegit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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/maxwellsdm1867/wheeler/resume)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/resume"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/resume.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.01426 |
| Opus 5 | $0.00013 | $0.00713 |
| Sonnet 5 | $0.00005 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
wh:resume 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 5d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, restoring context from a previous session. The scientist is back and needs to know where things stand.
Step 0: Query graph for active plans (graph-first)
Call query_plans(status="in-progress"). The query is already ordered by updated DESC, so the first row is the newest in-progress plan. This is the authoritative "where are we" source.
For each active plan, call query_notes(keyword="session-continuation") to fetch continuation notes linked to the plan. These hold the narrative context from /wh:pause.
Nothing-to-resume fast exit: If query_plans(status="in-progress") is empty AND .plans/STATE.md does not exist AND .plans/.continue-here.md does not exist, stop here. Say: "Nothing to resume. The graph has no in-progress plan and there's no saved session state. Run /wh:start to pick a next step." Do not continue to Steps 1-5.
Single in-progress fast path: If exactly one in-progress plan exists, lead with it in Step 5's summary as the obvious thing to resume (still confirm before any execute action).
Fall back to .plans/STATE.md only if the graph returns no plans (e.g., pre-migration projects). If falling back, warn that the project should be migrated to graph-first.
Step 1: Read plan files and continuation context
For each active plan from the graph, read the plan file (from the graph node's path) and any continuation note content. Also read .plans/.continue-here.md if it exists as a supplementary view.
Step 2: Check for additional plans
Call query_plans(status="approved") to find plans that are approved but not yet started. These may be the next work to pick up.
Step 3: Check Team Tasks
Use TaskList to check for results from a previous session's agent team. If tasks exist, summarize:
- Completed tasks and their results (use
TaskGetfor details) - In-progress or pending tasks that may need attention
- Flagged checkpoints awaiting judgment
Step 3b: Check Headless Logs (fallback)
If no team tasks found, run python -m wheeler.log_summary via Bash to see if any headless tasks completed since the last session. If there are unreviewed results, note them.
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.
- 5d ago First seen · 117 lines · 25 tokens per session scan A 3d884064035b
wh:resume is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,426 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
save
Save this conversation as a new or existing reusable context.
promote
Promote project-scoped instincts to global scope.