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/lykhoyda/rn-dev-agent/check-vercel-rulesgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWrote 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/lykhoyda/rn-dev-agent/check-vercel-rules)<a href="https://agentmods.dev/commands/lykhoyda/rn-dev-agent/check-vercel-rules"><img src="https://agentmods.dev/badge/commands/lykhoyda/rn-dev-agent/check-vercel-rules.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 | $0.00041 | $0.00750 |
| Opus 5 | $0.00020 | $0.00375 |
| Sonnet 5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
check-vercel-rules 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the Vercel rule audit: $ARGUMENTS
Why this command exists
The PostToolUse audit hook (hooks/vercel-rules-audit.sh) checks rules on
single-file edits during a session. This command runs the same checker
across a broader scope — the whole project, just changed files, or for
CI/pre-ship gating — and emits the chosen output format.
It wraps scripts/check-vercel-rules.mjs. Same checker, three call sites:
- PostToolUse hook (per edit, automatic)
- This slash command (manual, project-scoped)
- pre-ship-checker integration (CI, blocks on violations)
Modes
| Argument | Behavior |
|---|---|
| (none) | --all walk of cwd; reports violations; exit 0 |
--changed [files...] |
Check only specified files (or stdin one-per-line) |
--all |
Walk cwd for .tsx/.jsx/.ts/.js; max 200 files |
--ci |
Same as --all but exits 1 on any violation (use in pre-commit/CI) |
--baseline-snapshot |
Write current violations to baseline path; exit 0 |
--format hook|json|sarif |
Output shape (default hook) |
Run
# Default: --all on cwd, hook-format output
if [[ -z "$ARGUMENTS" ]]; then
node "${CLAUDE_PLUGIN_ROOT}/scripts/check-vercel-rules.mjs" --all
else
node "${CLAUDE_PLUGIN_ROOT}/scripts/check-vercel-rules.mjs" $ARGUMENTS
fi
After the run
- No violations → no output. The repo is clean against the v1.0 grep-checker subset.
- Violations reported → each line cites a rule ID and points to the
upstream rule file under
third_party/vercel-labs/agent-skills/skills/...for the full explanation + fix. - Want to suppress legacy violations? Run
/rn-dev-agent:check-vercel-rules --baseline-snapshotto snapshot the current set; subsequent runs (and the PostToolUse hook) will only report NEW violations. Critical for retrofit on existing codebases. - Want SARIF for GitHub code-scanning? Use
--format sarif; the output conforms to SARIF 2.1.0 and uploads cleanly to the Code Scanning API.
Reference
- Spec: https://github.com/Lykhoyda/rn-dev-agent-workspace/blob/main/docs/superpowers/specs/2026-05-07-vercel-skills-integration-design.md
- v1.0 checker scope (3 grep rules):
skills/rn-best-practices/SKILL.md§ Verification surface - Full rule corpus:
skills/rn-best-practices/rules.index.json(118 rules) - Upstream content:
third_party/vercel-labs/agent-skills/
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 · 65 lines · 41 tokens per session scan A 3846f1ec99b4
check-vercel-rules is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 750 once invoked, about $0.0002 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
dashboard-flow-auto
Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.
dashboard-flow-abort
Abort the running flow on a session. Usage /dashboard:flow-abort.
dashboard-git-branches
List git branches for the current dir (current marked ). Runs locally, no LLM.
brainstorm
Command dispatcher for brainstorm.
discover
Command dispatcher for discover.
propose
Command dispatcher for propose.