Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rafadorado/qrspivnpx agentmods add commands/rafadorado/qrspiv/outlineWrote 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/rafadorado/qrspiv/outline)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/outline"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/outline/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/rafadorado/qrspiv/outline"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/outline.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 | $0.00021 | $0.02139 |
| Opus 5 | $0.00010 | $0.01069 |
| Sonnet 5 | $0.00004 | $0.00428 |
| Haiku 4.5 | $0.00002 | $0.00214 |
Grade A, and why
outline 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 9d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure Outline (P Phase — Part 1)
If the design document is the destination, the outline is the route map. It shows the phases, their order, what new types and interfaces emerge, and where to verify correctness along the way. Think of it as C header files: signatures and types, not function bodies.
This is NOT a plan. Plans map ~1:1 to code and run 8+ pages. The outline is ~2 pages and stays at the structural level.
If individual file paths were provided, read them all fully.
If no parameters provided, respond with:
"I'll create a structure outline for your task. Point me to the thoughts folder (e.g., thoughts/001-auth-endpoint/), or provide the design document and research findings."
Then wait for the user's input.
If design.md is still draft or has unresolved open questions, stop and tell the user:
The design document still has unresolved questions. Please finalize it first:
run /qrspiv:design thoughts/<id>-<title>/
Do not proceed with an unapproved design.
For each phase, determine:
- What changes in this phase (files, components, layers)
- What depends on this phase completing before the next can start
- Where a meaningful verification checkpoint exists
Structure Outline: [Feature/Task Name]
Implementation Phases
Phase 1: [Name] — [one-line goal]
Changes: [which files/components/layers are touched] New types/interfaces:
TypeNameinpath/to/file.ext— [what it represents]functionSignature()inpath/to/file.ext— [what it does] Depends on: nothing (starting point) Verify: [how to confirm this phase works — test command, manual check, etc.]
Phase 2: [Name] — [one-line goal]
Changes: [which files/components/layers are touched] New types/interfaces:
- ... Depends on: Phase 1 Verify: [verification checkpoint]
Phase N: [Name] — [one-line goal]
...
Type & Interface Summary
[Compact listing of ALL new types, interfaces, and function signatures introduced across all phases. This is the "header file" view — everything in one place.]
Testing Checkpoints
[Ordered list: after each phase, what should pass]
- After Phase 1: [what to verify]
- After Phase 2: [what to verify] ... N. Final: [end-to-end verification]
Files Touched
[Complete list of files that will be created or modified, grouped by phase]
</template>
<critical>
- Stay structural. "Add a `RetryConfig` struct to `config/retry.go`" is good. "The struct should have fields for maxRetries (int), backoffMs (int)..." belongs in the plan, not here.
- New types and function signatures are the core value. If the outline doesn't show the shape of the new code, it's too vague.
- If the outline exceeds ~80 lines, you're writing a plan. Pull back to the structural level.
</critical>
</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.
- 9d ago First seen · 227 lines · 21 tokens per session scan A 0eb686f39f6f
outline is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 2,139 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
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.