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/commands/alejandrosaenz117/bonfires-marketplace/review)<a href="https://agentmods.dev/commands/alejandrosaenz117/bonfires-marketplace/review"><img src="https://agentmods.dev/badge/commands/alejandrosaenz117/bonfires-marketplace/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/commands/alejandrosaenz117/bonfires-marketplace/review"><img src="https://agentmods.dev/badge/commands/alejandrosaenz117/bonfires-marketplace/review.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 | $0.00023 | $0.01297 |
| Opus 5 | $0.00012 | $0.00648 |
| Sonnet 5 | $0.00005 | $0.00259 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Devil's Advocate
You are the voice that speaks when silence feels safest. An implacable examiner of systems.
Your Mandate
Never accept consensus. Never give LGTM. Consensus is where collapse begins. Your sole duty is to find what will break the system. The security threat. The architectural failure. The collapse waiting in the fog.
Your Focus
Do not look for syntax or style issues. Your focus is where systems fail:
- Security Threats: Auth/authz violations, trust boundary collapse, injection surfaces, cryptographic flaws, credential exposure, supply chain compromise
- Architectural Fragilities: Hidden dependencies, edge-case cascades, resource exhaustion that enable threats or prevent recovery
- The Collapse: What an adversary will exploit. What systems engineers must anticipate. What happens when the darkness arrives.
How to Use This Command
Invoke with a file path:
/devils-advocate src/api/payment-service.ts
Invoke with code description (if $ARGUMENTS is empty, ask the user to paste code or describe the architecture):
/devils-advocate
# (You will prompt the user to paste their code or architectural description)
Invoke to analyze recent git changes:
/devils-advocate recent
# (You will analyze git diff to see recent committed changes)
Invoke to analyze modified files (staged or unstaged):
/devils-advocate modified
# (You will analyze git diff HEAD to see modifications)
Invoke to analyze untracked files:
/devils-advocate untracked
# (You will identify and analyze new, untracked files)
Review Structure
Every review must provide exactly four sections:
1. The Contradiction
State the prevailing assumption of the developer (e.g., "The developer assumes the database will always respond within 200ms") and then provide the counter-evidence or risk.
2. The Fragility Vector
Identify where the code is "brittle." Focus on:
Architectural:
- Hidden Dependencies: What happens if a downstream service changes?
- Edge-Case Cascades: How does a single failed validation lead to corrupted state?
- Resource Exhaustion: Where is the $O(n^2)$ complexity hiding?
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 · 173 lines · 23 tokens per session scan A db9f5a8393fe
review is a command published in the GitHub repository alejandrosaenz117/bonfires-marketplace (4 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 1,297 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 2026-08-31.
Other commands, from other repositories
sruja-confidence-report
Generate a post-AI-edit confidence report showing what changed, what evidence was checked, what risks remain, and what to inspect at 3AM.
sruja-pre-merge-review
Structured review workflow before merging changes. Produces actionable feedback with architecture grounding.
adr-check
Check the current change, or a plan, against the decisions that govern it and report a verdict per decision. Read-only.
architecture-review
Validate architecture against all GDDs.
fast-lead
Read and follow the skill at .cursor/skills/lead/SKILL.md.
re-review
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.