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/rafadorado/qrspivWrote 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/plan)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/plan"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/plan.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 | $0.00016 | $0.01676 |
| Opus 5 | $0.00008 | $0.00838 |
| Sonnet 5 | $0.00003 | $0.00335 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
plan 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 7d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Plan (P Phase — Part 2)
The design answered "where are we going?" The outline answered "how do we get there?" The plan answers "what exactly do we write?" — specific file changes, code snippets, type definitions, and verification commands for each phase.
This is a tactical doc for the agent. The human has already aligned on direction (design) and structure (outline). The plan just fills in the implementation details. Spot-check it, don't deep-review it — save the deep review for the actual code.
If individual file paths were provided, read them all fully.
If no parameters provided, respond with:
"I'll create an implementation plan. Point me to the thoughts folder (e.g., thoughts/001-auth-endpoint/), or provide the outline and design documents."
Then wait for the user's input.
If either is unapproved or missing, stop and tell the user which step to complete first:
The [design/outline] is not yet approved. Please finalize it first:
run /qrspiv:[design|outline] thoughts/<id>-<title>/
Do not proceed without an approved outline.
For each phase, write:
- Overview — one paragraph restating the phase goal
- Changes Required — for each file touched:
- Full file path
- Summary of what changes
- Code snippets showing the specific additions or modifications (use the language's syntax)
- Reference to patterns from research.md that this code follows
- Success Criteria — split into:
- Automated Verification: commands that can be run (
make test,go test ./...,npm run typecheck, etc.) - Manual Verification: things a human should check (UI behavior, performance, edge cases)
- Automated Verification: commands that can be run (
Never plan all database changes first, then all services, then all API changes. That produces untestable intermediate states.
- Overview — 2-3 sentences on what we're implementing and why
- Current State — brief summary from research.md of what exists today
- Desired End State — from design.md, what the system looks like when done, and how to verify it
- What We're NOT Doing — out-of-scope items from the design's resolved decisions (prevents scope creep during implementation)
After the phases, include:
- Testing Strategy — unit tests, integration tests, and manual testing steps across the whole feature
- Files Touched — complete list grouped by phase (carried forward from outline)
[Feature/Task Name] Implementation Plan
Overview
[2-3 sentences: what and why]
Current State
[What exists today — key constraints from research]
Desired End State
[What the system looks like when done — verification criteria from design]
What We're NOT Doing
[Out-of-scope items — prevents scope creep]
Phase 1: [Name from outline]
Overview
[One paragraph: what this phase accomplishes]
Changes Required
1. [Component/File Group]
File: path/to/file.ext
Changes: [Summary]
// Specific code to add or modify
Pattern reference: follows [pattern name] from path/to/existing.ext
2. [Next Component/File Group]
...
Success Criteria
Automated Verification:
- [Test command]:
make test-xxxorgo test ./... - [Type check]:
npm run typecheck - [Lint]:
make lint
Manual Verification:
- [What to check manually]
Checkpoint: After automated verification passes, pause for human confirmation before proceeding to Phase 2.
Phase 2: [Name from outline]
[Same structure...]
Testing Strategy
Unit Tests:
- [What to test, which files]
Integration Tests:
- [End-to-end scenarios]
Manual Testing:
- [Specific steps]
Files Touched
Phase 1: file1 (new), file2 (modify)
Phase 2: file3 (new), file4 (modify)
...
</template>
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.
- 7d ago First seen · 211 lines · 16 tokens per session scan A 1651082831d9
plan is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 1,676 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.