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/validategit 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/validate)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/validate"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/validate.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 | $0.00016 | $0.01602 |
| Opus 5 | $0.00008 | $0.00801 |
| Sonnet 5 | $0.00003 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
validate 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate (V Phase)
- Functional — did we build what we set out to build? Compare the code against the design's desired end state and the task description.
- Patterns & style — does the new code follow the codebase's existing conventions? Are there antipatterns, style violations, or architectural shortcuts?
- Code quality — run the git-code-review skill for bugs, security, test coverage, and documentation.
This phase catches problems BEFORE commit and PR — fixing them here is far cheaper than in code review.
If no parameters provided, respond with:
"I'll validate the implementation. Point me to the thoughts folder (e.g., thoughts/001-auth-endpoint/), or I can validate the current branch changes directly."
Then wait for the user's input.
Read the design.md "Desired End State" section. For each stated outcome:
- Verify the code actually achieves it
- Run the end-to-end verification criteria from the design
- Check that "What We're NOT Doing" items were respected — no scope creep
Read the task.md and confirm the original problem is solved.
Present findings:
Functional validation:
Desired outcomes from design:
[x] [Outcome 1] — verified: [how]
[x] [Outcome 2] — verified: [how]
[ ] [Outcome 3] — NOT MET: [what's missing or wrong]
Scope check:
[x] No out-of-scope work introduced
or
[!] Scope creep detected: [what was added that shouldn't have been]
If any outcome is not met, present what is missing or broken — do not prescribe the fix. The human decides how to address it.
This step checks codebase-specific patterns: naming conventions, file organization, and integration points. Code style violations, architecture compliance, and security are covered by git-code-review in Step 3 — do not duplicate that work here.
Spawn parallel sub-agents:
- codebase-pattern-finder — find 2-3 existing files that do similar things to what was just built. Compare naming conventions and file organization.
- codebase-analyzer — trace the new code's integration points. Verify it connects to existing components in the expected way.
If agents return conflicting results or can't find sufficient examples, present the gap to the user and ask for guidance.
Present findings:
Pattern validation:
Conventions followed:
[x] [Convention] — matches pattern in `path/to/example.ext`
Deviations found:
[!] [Deviation] — new code does [X], existing pattern does [Y]
Reference: `path/to/existing.ext:line`
New code: `path/to/new.ext:line`
Do not label deviations as "wrong" — some deviations are intentional improvements. Present facts and let the user decide.
This covers: bugs and correctness, security (OWASP Top 10), code style, architecture compliance, test coverage, and documentation.
Wait for the review to complete and collect its summary.
If the review identifies issues that must be fixed (bugs, security problems, architectural violations), list them separately from suggestions:
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 · 194 lines · 16 tokens per session scan A 2fb0c266fc2e
validate 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 1,602 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.