Borrowing it
Nothing to install: this file belongs to motorway-sandbox/product-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/motorway-sandbox/product-os/main/.claude/commands/verify-source.mdgit clone --depth 1 https://github.com/motorway-sandbox/product-osWrote 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/motorway-sandbox/product-os/verify-source)<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/verify-source"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/verify-source.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 | $0.00000 | $0.01032 |
| Opus 5 | $0.00000 | $0.00516 |
| Sonnet 5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
verify-source 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Source
Review the evidence and insights presented earlier in this conversation for accuracy, confidence, and potential bias.
Run this command after asking for insights, evidence, or data analysis — it acts as a structured second pass to catch issues before you build on the findings.
Instructions
Before starting, read pm-playbook/evidence-standards/audit-criteria.md for the detailed evaluation criteria and pm-playbook/evidence-standards/output-template.md for the output format. If either file is missing, proceed using the audit steps below and the Key Principles section as your guide — the command still works without the reference files.
Step 1: Identify what to audit
Look back through the current conversation and identify all claims, insights, data points, and conclusions that were presented. List them as a numbered set of statements.
Step 2: Audit each statement
For each statement, evaluate against the criteria in pm-playbook/evidence-standards/audit-criteria.md:
- 2a. Source verification — check the cited source is correct, current, and accurately represented
- 2b. Confidence assessment — rate High / Medium / Low using the defined criteria
- 2c. Bias check — test for confirmation, survivorship, selection, anchoring, and correlation/causation biases
- 2d. dbt layer verification — for any quantitative claim, verify the underlying dbt model definition, health, and lineage
- 2e. Gaps and assumptions — identify missing evidence, unstated assumptions, and counter-evidence
Step 3: Search for counter-evidence
For any hypothesis or conclusion presented in the conversation:
- Identify the core claim
- Search relevant data files, research documents, and insight files for evidence that contradicts or complicates the claim
- Report what you find — even if the counter-evidence is weak, it's worth noting
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 · 79 lines · 0 tokens per session scan A 0bfc5c2d8360
verify-source is a command published in the GitHub repository motorway-sandbox/product-os (9 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,032 tokens. 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 2026-09-04.
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.