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/simonrowland/goal-flight/ask-questionsgit clone --depth 1 https://github.com/simonrowland/goal-flightWrote 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/simonrowland/goal-flight/ask-questions)<a href="https://agentmods.dev/commands/simonrowland/goal-flight/ask-questions"><img src="https://agentmods.dev/badge/commands/simonrowland/goal-flight/ask-questions.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 | $0.00027 | $0.01336 |
| Opus 5 | $0.00014 | $0.00668 |
| Sonnet 5 | $0.00005 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
ask-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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ask-questions [--scope ]
Read:
protocols/dispatch-routing.md
Spawn read-only workers to anticipate integration / requirements / snags questions. Surface only the ones with enough context to make sense to the user. Goal: clear ambiguities up front so the 12-hour unattended run doesn't stall on user input.
Modes
- Standalone:
/goal-flight ask-questions— user invokes explicitly between decompose-plan and execute (or any time). - Auto-chained: invoked at the end of
decompose-planwith--scope decomposition. - Continuous: invoked from inside
executewhen the orchestrator hits an ambiguity that requires user input.
Steps
1. Pick scope
| Scope arg | Anticipator focus |
|---|---|
decomposition (default after decompose-plan) |
Cross-chunk dependencies, ambiguous SCOPE/ACCEPTANCE wording, missing FORBIDDEN constraints |
<area> (e.g., auth, db-migration) |
Area-specific chunks; ignore unrelated work |
current-chunk (continuous mode) |
The chunk currently being executed; surface only blockers |
next-chunks (continuous mode, look-ahead) |
Next 1-2 upcoming chunks; non-blocking surfacing |
2. Spawn 1-2 anticipatory workers
Use read-only explorer workers through the host delegate operation with the prompt at prompts/ask-anticipatory.md (current Claude wrapper: Explore subagents; other hosts: adapter delegate equivalent). Substitute the scope and paths. Each worker:
- Scans the goal-queue, AGENTS.md, any binding-spec, recent git log.
- Generates
(question, default-answer, confidence, risk-if-wrong, second-opinion-suggestion)tuples. - For low-confidence items: notes "consider second opinion from <other ready, concern-diverse reviewer>" — for example, if the orchestrator's primary model is Claude in the current wrapper, use a codex/cursor/grok peer; if the orchestrator is codex, use a Claude-compatible/cursor/grok peer.
If two workers are spawned (recommended for decomposition scope; one is sufficient for current-chunk), run in parallel and dedupe results.
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.
- yesterday Changed · +2 lines · +16 tokens per session d561d8cf93bd
- 6d ago First seen · 99 lines · 11 tokens per session scan A 856525c1d3be
ask-questions is a command published in the GitHub repository simonrowland/goal-flight (20 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,336 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 2026-08-30.
Other commands, from other repositories
review-context7-updates
Please read the @README.md and @docs/tools/package-documentation.md to understand the high level context of my repo.
mine
Quickly capture relevant project context into Memento memory.
help
Show comprehensive Memento help — available MCP tools and usage patterns.
init
Set up Memento — configure MCP server and verify everything works.
search
Search your memories using Memento hybrid retrieval.
status
Show Memento server status and current configuration.