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/racecraft-lab/racecraft-plugins-public/validategit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/validate)<a href="https://agentmods.dev/commands/racecraft-lab/racecraft-plugins-public/validate"><img src="https://agentmods.dev/badge/commands/racecraft-lab/racecraft-plugins-public/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 | $0.00014 | $0.00672 |
| Opus 5 | $0.00007 | $0.00336 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
Deterministically verify that the implementation matches the specification by checking task completion, file existence, and requirement traceability.
Step 1: Select feature
If $ARGUMENTS specifies a feature name or number, use that. Otherwise, find the most recently modified feature in specs/.
If no features exist, error: "No features found in specs/. Run /speckit.specify first."
Step 2: Parse tasks
Read tasks.md from the feature directory. Parse each checkbox line:
- Extract task text (after
- [x]or- [ ]) - Mark as completed or remaining
- Extract keywords: file paths (
auth/login.py), snake_case names (user_auth), CamelCase names (UserAuth), dotted names (config.yaml)
If no tasks.md exists, error: "No tasks.md found. Run /speckit.tasks first."
Step 3: Verify completed task artifacts
For each completed task that references file paths:
- Search the project directory for the referenced file
- If found: PASS
- If not found: WARN ("task says 'Create auth/login.py' but file not found")
Skip verification for:
- Incomplete tasks (not yet implemented)
- Tasks with no file path references (e.g., "Set up CI pipeline")
Step 4: Parse spec requirements
Read spec.md from the feature directory. Extract items from the "Functional Requirements" section (bulleted list items under that heading).
If no requirements section found, skip to Step 6.
Step 5: Trace requirements to tasks
For each requirement, search task descriptions for matching keywords:
- Tokenize the requirement into significant words (skip stop words)
- Check each task's text for overlap (2+ matching keywords = traced)
Report:
- Requirement with matching tasks: PASS ("traced to Task N")
- Requirement with no matching tasks: WARN ("no task found for this requirement")
Step 6: Report
Output a validation report:
Validation Report: 001-auth
============================
Task Completion: 3/5 (60%)
[x] Task 1: Create auth/login.py -> auth/login.py FOUND
[x] Task 2: Add password hashing -> (no file reference)
[x] Task 3: Write auth tests -> tests/test_auth.py FOUND
[ ] Task 4: Add rate limiting -> (not yet implemented)
[ ] Task 5: Update API docs -> (not yet implemented)
Requirement Traceability: 3/3
"Users can log in with email" -> Task 1 (PASS)
"Passwords are stored securely" -> Task 2 (PASS)
"Users can reset password via email" -> (no matching task - WARN)
Summary: 2 PASS, 1 WARN, 0 FAIL
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.
- 4d ago First seen · 81 lines · 14 tokens per session scan A 9836a84f2c9e
validate is a command published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 672 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
build
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
deepen
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
research
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.
review
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
spec
Create, amend, or backprop bug into SPEC.md. Sole mutator of spec.
check
Drift detector. Diff SPEC.md against code. Read-only, zero writes.