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/alejandrosaenz117/bonfires-marketplaceWrote 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/plugins/alejandrosaenz117/bonfires-marketplace/devils-advocate)<a href="https://agentmods.dev/plugins/alejandrosaenz117/bonfires-marketplace/devils-advocate"><img src="https://agentmods.dev/badge/plugins/alejandrosaenz117/bonfires-marketplace/devils-advocate/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/plugins/alejandrosaenz117/bonfires-marketplace/devils-advocate"><img src="https://agentmods.dev/badge/plugins/alejandrosaenz117/bonfires-marketplace/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
devils-advocate 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 10d 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
{
"name": "devils-advocate",
"version": "0.1.0",
"description": "Adversarial security and architectural code review. Finds the most plausible security failure in your code.",
"author": {
"name": "Alejandro Saenz",
"url": "https://github.com/alejandrosaenz117"
},
"license": "MIT",
"homepage": "https://github.com/alejandrosaenz117/bonfires-marketplace",
"repository": "https://github.com/alejandrosaenz117/bonfires-marketplace",
"keywords": ["security", "code-review", "adversarial", "architecture", "threat-modeling"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 1 agent travel with it, and installing the plugin installs all of them — 140 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 10d ago First seen · 14 lines scan A 0bbc23e599eb
devils-advocate is a plugin published in the GitHub repository alejandrosaenz117/bonfires-marketplace (4 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
deep-plan
AI-assisted deep planning with research, interview, external LLM review, and TDD approach.
fakoli-plugin-critic
Five specialist critic agents for Claude Code plugin development — agent-critic (frontmatter/color/tools), skill-critic (lazy-loading/no-fuzzy-detection), hook-critic (contract-aware/${CLAUDEPLUGINROOT}), mcp-critic (schema/actor-validation), structure-critic (manifest/CHANGELOG/version-sync). Audit any plugin (your.
gh-review-loop
Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped so it can never spam the PR. Works with Codex out of the box, or any reviewer bot you configure.
dev-workflow-forge
A generator kit for Claude Code dev tooling. Three generators read your codebase and write a project-specific review skill, a rules set, and a self-learning feedback loop tuned to your stack, instead of handing you tooling written for someone else's project. The review skill they write is an overlay on a shared engine.
role-lenses
Six senior-review lenses as slash commands. Each drops Claude into a specific principal-level seat (architect, critic, design, ops, pm, staff) with its own refusals and output contract, so you get a pointed second opinion instead of agreement.
search-visibility
Two halves of getting found: a-seo-gsc pulls your Google Search Console data over the API (or reads a manual export) and turns it into a prioritized action plan backed by your own numbers, and a-geo-optimizer checks whether AI assistants can fetch, parse, and cite a site, then recommends the technical and content…