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.
git clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/plan-open-questions)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-open-questions"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-open-questions/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.
<a href="https://agentmods.dev/commands/oborchers/fractional-cto/plan-open-questions"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/plan-open-questions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.04751 |
| Opus 5.5 | $0.00046 | $0.01900 |
| Sonnet 5.5 | $0.00023 | $0.00950 |
| Haiku 4.5 | $0.00011 | $0.00475 |
Grade A, and why
plan-open-questions 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are walking the user through a set of open questions. For each question you (a) ground the analysis in whatever evidence exists, (b) print a fixed short block, (c) make one AskUserQuestion call carrying exactly that one question with 2–4 alternatives, and (d) record the user's choice. Questions are walked strictly sequentially — you finish presenting, asking, and capturing one question before you touch the next. After all questions are walked you print a summary, and — only when the source is a master plan file — apply the answers to it.
Never batch. AskUserQuestion accepts up to 4 questions in a single call. Never use that to ask several open questions at once. One open question = one AskUserQuestion call. The user resolves each question in isolation.
This command runs entirely in the main conversation. Do not dispatch a subagent. All reading, analysis, and alternative-generation happens here.
Everything you print follows planning-tools:plain-language. Short sentences. One idea each. Every ticket, ADR, and PR carries its human name, not just its ID.
Input: $ARGUMENTS
Parse arguments:
- First positional path → explicit source file (skips the rest of the ladder).
- First or second positional integer → single-question targeting (walks only that Q-number).
- No args → resolve the source via the ladder in Step 1, walk all open questions.
Step 1 — Resolve the question source
Open questions do not only live in master plans. Work down this ladder and stop at the first rung that yields questions. Do not hard-fail at any rung — fall through to the next one.
Rung 1 — Explicit path argument
If the user supplied a path, Read it. If the Read fails, report the failed path and go to Rung 4 (do not silently fall through to branch matching — the user named a file and deserves to know it was not there).
Rung 2 — Already in this conversation
Before touching the filesystem, check what is already in context. Use it if you find any of:
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 · 362 lines · 114 tokens per session scan A 892fda99bd0f
plan-open-questions is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 114 tokens to every session and 4,751 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-13.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.