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/handoffgit 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/handoff)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/handoff"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/handoff.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 | $0.00019 | $0.02109 |
| Opus 5 | $0.00010 | $0.01055 |
| Sonnet 5 | $0.00004 | $0.00422 |
| Haiku 4.5 | $0.00002 | $0.00211 |
Grade A, and why
wh:handoff 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 4d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, a co-scientist at the HANDOFF transition point. The scientist and Wheeler have been thinking together, and you're evaluating whether remaining work can run independently.
The Core Rule
Every factual claim MUST cite a knowledge graph node using [NODE_ID] format.
Your Job
Assess context saturation and propose tasks for independent execution.
Pre-flight: Close-Readiness Check
Before queueing any background work, verify the foreground session has captured its provenance. Background workers should not run on top of an unclosed session with orphaned questions, unsupported hypotheses, or graph/file drift: they will produce results that cannot be cleanly traced back to the conversation that generated them.
Opt-out: If $ARGUMENTS contains --skip-close, skip this entire section, note "User opted out of close-readiness check via --skip-close" in the handoff report, and proceed directly to step 1 below.
Otherwise:
-
Call
graph_gaps()to detect relationship-based provenance gaps (unlinked questions, unsupported hypotheses, executions with no outputs, findings not appearing in any document, orphaned papers). -
Call
graph_consistency_check(repair=False)to detect drift between the graph,knowledge/*.json, andsynthesis/*.mdlayers. -
Compute
total_gaps = unlinked_questions + unsupported_hypotheses + idle_executions + orphan_findings + orphan_papersfrom thegraph_gapsresult. Computedrift_countfrom thegraph_consistency_checkresult (sum of mismatches across layers). -
If
total_gaps > 0ORdrift_count > 0, present this prompt to the user verbatim, filling in the actual counts:This session has uncaptured provenance: - <N> unlinked questions - <N> unsupported hypotheses - <N> stale analyses - <consistency drift if any> Recommend running /wh:close first to capture provenance before queueing background workers. Run /wh:close first? (Y/n) -
Honor the answer:
- Y (or any affirmative): Stop the handoff. Tell the user: "Run /wh:close to sweep provenance, then re-invoke /wh:handoff." Do not proceed to step 1 of the protocol below.
- N (or any negative): Note in the handoff report: "User declined pre-close check, queueing background workers with orphans / drift entries." Then proceed to step 1 of the protocol below.
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.
- 4d ago First seen · 177 lines · 19 tokens per session scan A 23c693dd7652
wh:handoff is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,109 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
analysis
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
status
Show the current status of a NanoResearch workspace.
search
Fuzzy-search CrossRef by title. Args: "title query.
migrate-server
迁移服务器端旧项目数据到 v5 结构.
rebuttal-init
交互式初始化 Rebuttal 项目.
git
Git operations with intelligent commit messages and workflow optimization.