Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add IgorGanapolsky/ThumbGate/plugin install codex-bridgeWrote 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/igorganapolsky/thumbgate/adversarial-review)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/adversarial-review"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/adversarial-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/igorganapolsky/thumbgate/adversarial-review"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/adversarial-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 | $0.00042 | $0.00220 |
| Opus 5 | $0.00021 | $0.00110 |
| Sonnet 5 | $0.00008 | $0.00044 |
| Haiku 4.5 | $0.00004 | $0.00022 |
Grade A, and why
adversarial-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Adversarial Review
Default to the current uncommitted workspace unless the user explicitly provides base=<branch> or commit=<sha>.
Run one of:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" adversarial-review --uncommitted
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" adversarial-review --base main
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" adversarial-review --commit <sha>
If the user asks for a specific threat model such as security, rollback safety, billing, or data loss, pass that in --prompt.
When reporting back:
- lead with concrete risks
- separate proven issues from speculation
- mention the saved artifact path if the user wants the full Codex output
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.
- 11d ago First seen · 25 lines · 42 tokens per session scan A 82f062709822
adversarial-review is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 220 once invoked, about $0.0002 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
reviewing-code-quality
Reviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict. Use when a change risks oversized files, needless layers, feature logic leaking into shared code, or clever indirection. Do not use for a trivial obvious edit, or for a check that is only about whether…
clean-code-review
Run a comprehensive Clean Code audit against the codebase — module size, function complexity, long parameter lists, TODO/FIXME markers, commented-out code, duplication (DRY), Boy Scout delta, dead exports, test smells, shell-parity (PS/Bash twins), dep boundaries (cross-package imports), frozen-arrays drift…
code-review
Plan-Forge-tuned comprehensive code review — runs public-surface diff, forge analysis, architecture / security / testing / patterns checks, plus Plan-Forge-specific gates (ACI compliance, dual-shell parity, branch model). Use before merging features or at the end of a phase. With --quorum, dispatches multi-model…
forge-quench
Systematically reduce .NET/C# code complexity while preserving exact behavior — measure, understand, propose, prove, report. Use after a feature is complete and tests pass, when code works but is harder to maintain than it should be.
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.