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/rafadorado/qrspiv/implementgit 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/implement)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/implement"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/implement.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 | $0.00013 | $0.01114 |
| Opus 5 | $0.00006 | $0.00557 |
| Sonnet 5 | $0.00003 | $0.00223 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
implement 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan (I Phase)
The plan contains exact file changes, code snippets, and verification commands for each phase. Your job is to follow the plan faithfully while adapting to what you actually find in the codebase. The plan is your guide — but the code is the truth.
By default, implement ONE phase per invocation. The user can request multiple phases explicitly.
Also read all codebase files referenced in the current phase's "Changes Required" section.
If a specific phase was requested (e.g., thoughts/001-auth-endpoint/ phase 2), skip to that phase.
If no parameters provided, respond with:
"I'll implement a plan for you. Point me to the thoughts folder (e.g., thoughts/001-auth-endpoint/), or provide the plan file directly."
Then wait for the user's input.
- If no checkmarks exist, start at Phase 1.
- If checkmarks exist, find the first unchecked phase and start there. Trust that completed phases are done — only re-verify previous work if something seems off.
Confirm with the user which phase you're about to implement:
Starting Phase [N]: [Name]
[One-line summary of what this phase does]
Proceeding with implementation.
- Read each file to be modified FULLY before changing it
- Write the code changes specified in the plan
- Follow pattern references — if the plan says "follows pattern from
path/to/existing.ext", read that file and match its naming, structure, error handling style, and conventions in your new code - Create new files where specified
Mismatch in Phase [N]:
Plan expects: [what the plan says]
Codebase has: [what actually exists]
Impact: [why this matters for the implementation]
How should I proceed?
Wait for the user's guidance before continuing.
After all automated checks pass, check off the automated items in the plan file using Edit, then pause:
Phase [N] complete — ready for your review.
Automated verification passed:
- [x] `make test-xxx` — passed
- [x] `npm run typecheck` — passed
[list each command that was actually run]
Manual verification for you to check:
- [ ] [Each manual item from the plan's "Manual Verification" section]
Reply 'proceed' when you've reviewed and I'll continue to Phase [N+1].
If the phase has no manual verification items, say: "No manual verification needed for this phase — automated checks are sufficient."
Do not check off manual verification items — only the user can confirm those.
All phases complete for thoughts/<id>-<title>/.
Your work item's QRSPI trail:
task.md ← what we're building
questions.md ← what we researched
research.md ← what we found
design.md ← where we're going
outline.md ← how we get there
plan.md ← exact steps (all checked off)
Next step: run /qrspiv:validate thoughts/<id>-<title>/
This checks functional correctness, pattern compliance, and code quality before you commit.
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.
- 3d ago First seen · 127 lines · 13 tokens per session scan A 4fd591ee0751
implement is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,114 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
git
Git operations with intelligent commit messages and workflow optimization.
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.