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/pausegit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWhat 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 | $0.00023 | $0.01895 |
| Opus 5 | $0.00012 | $0.00948 |
| Sonnet 5 | $0.00005 | $0.00379 |
| Haiku 4.5 | $0.00002 | $0.00189 |
Grade A, and why
wh:pause 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, capturing the current investigation state so the scientist can resume later — possibly in a new Claude Code session with no memory of this conversation.
Your Job
Write a .plans/.continue-here.md file that gives a future Wheeler session everything it needs to pick up where we left off.
What to Capture
Review the full conversation and extract:
1. Current Position
- What investigation/question we're working on
- Which mode we were in (planning, executing, writing, etc.)
- Active plan file (if any in
.plans/)
2. What's Done
- Decisions made during this session
- Findings added to the graph (cite [NODE_ID])
- Tasks completed
- Key conclusions reached
3. What's Pending
- Tasks approved but not yet executed
- Analysis in progress
- Handoff tasks queued or proposed
4. Team Task Status
If an agent team is active, use TaskList and TaskGet to capture:
- Team name
- Completed tasks and their results
- In-progress tasks
- Pending/blocked tasks
- Any checkpoint messages received
Include this in the .continue-here.md so the next session knows to check TaskList.
5. Open Decisions
- Checkpoints flagged but not resolved
- Forks where we haven't chosen a direction
- Questions the scientist needs to answer
6. Context That Would Be Lost
- Insights from discussion that aren't in the graph yet
- Reasoning behind decisions (the "why" that's only in conversation)
- Hypotheses discussed but not formally recorded
7. Suggested Next Action
- What the scientist should do when they return
- Which
/wh:*command to start with
File Format
# Continue Here
Paused: <timestamp>
Investigation: <name or topic>
Last mode: <plan|chat|execute|write|etc.>
Active plan: <path or "none">
Active team: <team name or "none">
## Current Position
<Where we are in the investigation>
## Completed This Session
- <what got done, with [NODE_ID] citations>
## Pending
- <what's queued or in progress>
## Team Status
<team task summary if active, or "No active team">
## Open Threads
<one line per new OpenQuestion created in this session's sweep>
- [Q-xxxx] <question text> (priority N)
- [Q-yyyy] <question text> (priority N)
<or "None — no unresolved threads from this session." if the sweep produced none>
## Open Decisions
- <checkpoints, forks, questions needing judgment that are NOT yet Q-xxxx nodes>
## Context Notes
<Insights and reasoning from conversation. Pointers to the [F-xxxx] and [N-xxxx] registered during the intermediate-artifact sweep — do NOT re-paste their full content here; the graph holds it.>
## Resume With
`/wh:<command>` — <why this is the right next step>
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 · 159 lines · 23 tokens per session scan A 55bd9ac38f36
wh:pause is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 1,895 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
export
Export a knowledge abstract to an Obsidian vault — a folder of Markdown notes linked by [[wikilinks]].
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
maestro-issue
Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 关掉 ISS-xxx / 关联到 task / 扫描发现问题) and the workflow routes to the right operation. Operates on .workflow/issues/. 知识管理走 /maestro-knowledge；knowhow 沉淀走 /maestro-knowhow；约束规则走 /maestro-spec。Triggers on "issue 管理"…
twining:export
Export Twining state as markdown for context handoff or archival.
formula-f10
../../../core/thinkingos/agents/observer.md.
formula-f8
../../../core/thinkingos/agents/securityauditor.md.