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/sebuzdugan/fraiWrote 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/sebuzdugan/frai/rai-spec)<a href="https://agentmods.dev/commands/sebuzdugan/frai/rai-spec"><img src="https://agentmods.dev/badge/commands/sebuzdugan/frai/rai-spec.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 | $0.00015 | $0.00253 |
| Opus 5 | $0.00008 | $0.00127 |
| Sonnet 5 | $0.00003 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
rai-spec 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 9d 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.
What it actually says
Follow the FRAI Gate workflow (canonical skill: github.com/sebuzdugan/frai-skills,
skill responsible-ai-spec; local template: packages/frai-gate/assets/rai-spec-template.md).
Task: $ARGUMENTS
- If the argument is a feature idea: classify its EU AI Act risk tier (prohibited / high / limited / minimal), then write a spec from the template with every FRAI Gate field answered concretely - seven checks: risk tier, data & privacy, human oversight, evaluation thresholds, bias & fairness, monitoring & rollback, transparency & incidents. Ground answers in this repository's actual code; every answer needs a number, a name, or a mechanism. Flag anything needing a human decision as "NEEDS HUMAN INPUT".
- If the argument is a path to an existing spec: run
node packages/frai-gate/dist/cli.js check <path>and explain each finding with the specific fix. - If no argument: ask what feature to spec.
Hard rule: high-risk tier requires a named human sign-off - never self-approve it.
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.
- 9d ago First seen · 22 lines · 15 tokens per session scan A 2cc3749e1b6b
rai-spec is a command published in the GitHub repository sebuzdugan/frai (53 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 253 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 2026-08-30.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
review-policy
Review a policy document for structure, coverage, and language quality.
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.