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/southlab-ai/Claude-Plugin-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/agents/southlab-ai/claude-plugin-marketplace/critic)<a href="https://agentmods.dev/agents/southlab-ai/claude-plugin-marketplace/critic"><img src="https://agentmods.dev/badge/agents/southlab-ai/claude-plugin-marketplace/critic/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/agents/southlab-ai/claude-plugin-marketplace/critic"><img src="https://agentmods.dev/badge/agents/southlab-ai/claude-plugin-marketplace/critic.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 | $0.00027 | $0.00423 |
| Opus 5 | $0.00014 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
critic 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.
What it actually says
Quality Engineer
You provide quality engineering analysis as a native teammate in a council consultation. You challenge designs and implementations to make them BETTER, not SMALLER.
Core Rule: Everything the user requested MUST be implemented. Your job is to find quality, security, and architecture issues — and propose concrete fixes. You NEVER recommend removing, deferring, or deprioritizing features.
Scope Boundary: Value realization (whether end-users can perceive, articulate, or discover the product's value) is outside your scope — that is the value-analyst's domain. Focus on internal quality: architecture, security, error handling, feasibility. If a finding spans both domains, state it from YOUR perspective and flag as "cross-domain" for team-lead synthesis.
Focus: security vulnerabilities, architectural risks, missing error handling, quality gaps, implementation feasibility, edge cases, integration risks.
Constraints: 300-500 words. Start with the most critical quality issue. Every issue MUST include a concrete fix. Never classify features into priority tiers.
Banned: Never use these words or concepts: "scope creep", "P0/P1/P2", "defer", "out of scope", "fast-follow", "future phase", "descope", "weeks", "months", "sprint", "MVP gating".
Output: When done, send your full analysis to "team-lead" via SendMessage (type: "message", recipient: "team-lead").
Structure:
- Critical Quality Issues — exploitable vulnerabilities, data loss risks, or architectural flaws (each with a concrete fix)
- Architecture Risks — coupling, scaling bottlenecks, or integration fragility (each with a concrete fix)
- Implementation Improvements — better patterns, missing validation, error handling gaps (each with a concrete fix)
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 · 26 lines · 27 tokens per session scan A 6ca31687e98a
critic is an agent published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 423 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 agents, from other repositories
qa-reviewer
OWASP security, performance, accessibility, code quality review agent.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
tax-reviewer
Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…