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/sorah/configWrote 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/sorah/config/validate)<a href="https://agentmods.dev/commands/sorah/config/validate"><img src="https://agentmods.dev/badge/commands/sorah/config/validate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sorah/config/validate"><img src="https://agentmods.dev/badge/commands/sorah/config/validate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.01549 |
| Opus 5.5 | $0.00007 | $0.00620 |
| Sonnet 5.5 | $0.00004 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate a completed implementation against its spec. Read both the spec and all implemented code, then systematically compare them. Surface every gap, discrepancy, or deviation for the user to resolve — do not silently accept or fix differences. The goal is to ensure the implementation faithfully reflects the spec, or to explicitly document where and why they diverge.
Input
The user provides a spec file path as argument: $ARGUMENTS
If no argument is given, ask the user which spec file to validate.
Preparation Phase
Before comparing anything:
- Read the spec file thoroughly — understand the full design, all deliverables, schemas, behavior descriptions, error handling, and edge cases
- Read all referenced files — schema files, existing code, related specs mentioned in the spec
- Review recent changes — use
git diffand recent commits up to the primary branch to understand what changed as part of this implementation. This gives context on the actual scope of changes and helps identify modifications the spec may not have anticipated - Read project conventions — check for project-level documentation (CLAUDE.md, style guides, architecture docs, knowledge files) relevant to the spec's domain. Project-specific conventions and framework-specific skills always take priority over general approaches
- Identify all deliverables — build a complete list of files and changes the spec calls for, from the Deliverables section and the Current Status checklist
- Read every delivered file — read each file listed in the deliverables. If a file doesn't exist, note it as missing. If the spec mentions modifications to existing files, read those files too
- Explore surrounding code — look at related modules, tests, and integration points to understand how the implementation fits into the broader codebase
Validation Phase
Compare the implementation against the spec systematically. Check each area below and record every discrepancy found, no matter how small.
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.
- yesterday First seen · 145 lines · 18 tokens per session scan A 1649d095800d
validate is a command published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,549 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.
Other commands, from other repositories
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
test-value-review
Use when a diff adds or changes test files, when a PR claims coverage for config, CI workflows, templates, or HTML output, or when tests look written only to satisfy a "must have tests" rule; not for Playwright selector or performance hygiene (use /playwright-review).
auditar-refactor
Invoca refactor-safety-auditor — gate canônico antes de qualquer refactor. Coleta evidências (linhas, contrato externo, coverage, mutation) e retorna veredito GO/BLOCK/WARN/GO-OVERRIDE.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.