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 skills add ThibautBaissac/rails_ai_agents --skill dependabot-reviewgit clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agentsWrote 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/skills/thibautbaissac/rails_ai_agents/dependabot-review)<a href="https://agentmods.dev/skills/thibautbaissac/rails_ai_agents/dependabot-review"><img src="https://agentmods.dev/badge/skills/thibautbaissac/rails_ai_agents/dependabot-review/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/skills/thibautbaissac/rails_ai_agents/dependabot-review"><img src="https://agentmods.dev/badge/skills/thibautbaissac/rails_ai_agents/dependabot-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 243 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Tool Misuse · line 261 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00089 | $0.03715 |
| Opus 5 | $0.00044 | $0.01858 |
| Sonnet 5 | $0.00018 | $0.00743 |
| Haiku 4.5 | $0.00009 | $0.00371 |
Grade A, and why
dependabot-review 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 12d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot Gem Upgrade Review
Current repo: !gh repo view --json nameWithOwner -q .nameWithOwner 2>/dev/null || echo "(unknown — run from inside the repo)"
Review Dependabot PRs and give the developer a concise, scannable verdict: what changed upstream, what could break (and how to fix it), what each gem touches in the codebase, and whether to merge.
Trigger phrases for audit mode: "review all open dependabot PRs", "which dependabot PRs are ready to merge", "audit our dep upgrades", "go through the open dep PRs", "check dependabot", any request for a status/report on pending dependency updates. Trigger single-PR mode on any GitHub PR URL related to dependabot, gem upgrades, or "bump" in the title. If the intent is ambiguous, default to audit mode.
Choosing a mode
Pick the mode based on what the user asked for:
- Single-PR mode — the user pasted a specific Dependabot PR URL or otherwise referenced one PR. Run the single-PR workflow below.
- Audit mode — the user asked about all open Dependabot PRs (phrases like "audit our deps", "review open dependabot PRs", "which dep upgrades are safe to merge"). Run the audit workflow. Do not ask the user to paste URLs — discover them with
gh.
If the intent is ambiguous (e.g., "review dependabot"), default to audit mode since it's the superset and shows what's available.
Audit workflow (multiple PRs)
Step A1: Discover open Dependabot PRs
Determine the repo from the current working directory (gh repo view --json nameWithOwner -q .nameWithOwner). Then list open Dependabot PRs:
gh pr list --author "app/dependabot" --state open \
--json number,title,url,createdAt,headRefName,labels \
--limit 50
The app/ prefix in the author filter is required — Dependabot authors as the bot account app/dependabot. If gh returns an empty list, tell the user "No open Dependabot PRs in ." and stop.
Before diving into analysis, surface the scope to the user in one line: "Found N open Dependabot PRs. Analyzing each now…" — this sets expectations when there are many to crunch through.
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.
- 12d ago First seen · 272 lines · 89 tokens per session scan A 8c032b436c4c
dependabot-review is a skill published in the GitHub repository ThibautBaissac/rails_ai_agents (661 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 3,715 once invoked, about $0.0004 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…