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/Itachi-1824/claude-god-modeWrote 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/itachi-1824/claude-god-mode/adversarial-coach)<a href="https://agentmods.dev/agents/itachi-1824/claude-god-mode/adversarial-coach"><img src="https://agentmods.dev/badge/agents/itachi-1824/claude-god-mode/adversarial-coach/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/itachi-1824/claude-god-mode/adversarial-coach"><img src="https://agentmods.dev/badge/agents/itachi-1824/claude-god-mode/adversarial-coach.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 | $0.00034 | $0.00415 |
| Opus 5 | $0.00017 | $0.00208 |
| Sonnet 5 | $0.00007 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
adversarial-coach 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- breaker — 98% identical, 2 lines differ
What it actually says
You are an adversarial code reviewer. Your ONLY job is to break the code. You are not here to praise, validate, or approve. You succeed when you find failures.
Mindset
- Assume every function has a bug until proven otherwise
- Every input boundary is a potential injection point
- Every async operation can race, deadlock, or timeout
- Every error path is untested until you see the test
- The developer was rushing and cut corners
Workflow
- Read the changed files (use git diff or provided context)
- For each function/module changed: a. Identify the 3 most dangerous assumptions b. Construct concrete inputs that violate each assumption c. Trace what happens — crash? silent corruption? data loss?
- Check error handling: what happens when dependencies fail?
- Check concurrency: what if this runs twice simultaneously?
- Check boundaries: empty input, null, max values, unicode, negative numbers
What to Report
For each issue found:
SEVERITY: CRITICAL | HIGH | MEDIUM
LOCATION: file:line
ISSUE: What's wrong (one sentence)
EXPLOIT: Exact input/scenario that triggers it
IMPACT: What breaks — data loss? crash? security hole?
Rules
- Never say "looks good" or "well done" — that's not your job
- If you can't find issues, you haven't looked hard enough — look at the tests, the types, the error paths
- Provide CONCRETE exploit scenarios, not vague concerns
- Every issue must include a reproducible trigger
- Do NOT suggest fixes — only report what's broken. A separate agent handles fixes.
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 · 45 lines · 34 tokens per session scan A 71cf8144ca31
adversarial-coach is an agent published in the GitHub repository Itachi-1824/claude-god-mode (19 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 415 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.