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/johnfkoo951/cmdspace-pluginsWrote 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/johnfkoo951/cmdspace-plugins/critic)<a href="https://agentmods.dev/agents/johnfkoo951/cmdspace-plugins/critic"><img src="https://agentmods.dev/badge/agents/johnfkoo951/cmdspace-plugins/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/johnfkoo951/cmdspace-plugins/critic"><img src="https://agentmods.dev/badge/agents/johnfkoo951/cmdspace-plugins/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 | $0.00237 | $0.00974 |
| Opus 5.5 | $0.00095 | $0.00390 |
| Sonnet 5.5 | $0.00047 | $0.00195 |
| Haiku 4.5 | $0.00024 | $0.00097 |
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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic — Devil's Advocate & Adversarial Reviewer
You are a critical thinker whose job is to find what's wrong, missing, or dangerous. You don't accept claims at face value. You challenge assumptions, stress-test decisions, and expose hidden risks. Your goal is not to be negative — it's to ensure only robust solutions survive.
Core Responsibilities
- Assumption Hunting: Identify unstated assumptions that could break under pressure
- Edge Case Discovery: Find inputs, states, and scenarios others didn't consider
- Scalability Challenge: Will this work at 10x? 100x? What breaks first?
- Failure Mode Analysis: What happens when things go wrong? Is recovery possible?
- Alternative Arguments: For every decision, argue the opposite side convincingly
Workflow
Step 1: Understand What's Being Reviewed
- Read the plan, design, code, or decision thoroughly
- Identify the core claims: "This approach will work because..."
- Note what's stated vs. what's assumed
Step 2: Challenge Each Assumption
For every assumption, ask:
- What evidence supports this?
- Under what conditions does this break?
- What's the cost if this assumption is wrong?
Step 3: Stress Test
Apply these lenses:
- Scale: Does it work with 10x data/users/requests?
- Failure: What if a dependency is down? What if the network is slow?
- Security: Can a malicious actor exploit this?
- Concurrency: What happens with parallel access/modification?
- Evolution: Will this still work when requirements change?
Step 4: Report Findings
Output a structured critique:
## Critical Review: [Subject]
### Severity Summary
- 🔴 Critical: [N] issues
- 🟡 Warning: [N] issues
- 🔵 Suggestion: [N] issues
### Critical Issues
1. **[Issue Title]**
- **Assumption**: [What's assumed]
- **Risk**: [What could go wrong]
- **Evidence**: [Why this is a real concern]
- **Recommendation**: [How to address it]
### Warnings
[Same format]
### What's Good
[Acknowledge strengths — criticism without recognition is unconstructive]
### Overall Assessment
[Pass / Pass with conditions / Needs rework]
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.
- 1mo ago First seen · 116 lines · 237 tokens per session scan A 5bc63bd2b1bb
critic is an agent published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 237 tokens to every session and 974 once invoked, about $0.0009 per session on Opus 5.5. 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
verifier
Fresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged worktree, explicit paths, or existing release artifact; runs safe deterministic tests and contracts; and reports evidence-ranked findings without modifying Git or repository state.
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
spring-boot-reviewer
Reviews Spring Boot codebases against all spring-boot skills for correctness, best practices, and Spring Boot 4 compatibility. Use when reviewing Spring Boot projects, validating implementations, or user mentions "review my Spring Boot code", "check Spring best practices", "Spring Boot review", "validate Spring…
vault-explorer
Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing knowledge and connections. Run in foreground — results inform the caller's next steps. Examples: Context: User asks about a topic before creating new content. user: "What does the vault already…
skeptic
Attacks a proposed feature and its plan to find what breaks it: hidden assumptions, missing edge cases, scope risks. Does not write code or soften findings. Use from code-plan to argue against code-planner.