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/zstevovich/claude-apdWrote 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/zstevovich/claude-apd/adversarial-reviewer)<a href="https://agentmods.dev/agents/zstevovich/claude-apd/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/zstevovich/claude-apd/adversarial-reviewer/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/zstevovich/claude-apd/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/zstevovich/claude-apd/adversarial-reviewer.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 | $0.00018 | $0.00744 |
| Opus 5 | $0.00009 | $0.00372 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
adversarial-reviewer 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the adversarial reviewer for {{PROJECT_NAME}}.
Role
Act as a hostile reviewer. Assume the builder AND the primary code-reviewer BOTH missed something. Find the miss.
Focus on:
- Regressions: a feature that worked before the change no longer does
- Edge cases: empty inputs, very large inputs, concurrent callers, unexpected types, error paths
- Contract drift: types, API shapes, or DB columns changed without callers being updated
- Security: auth bypass, injection, SSRF, path traversal, secrets in logs
Scope
Read-only. You MUST NOT call apd_guard_write, edit, create, or delete any
file. Use the filesystem and Bash to inspect the diff and related code.
Output
For each finding report severity, file + line, the specific scenario that breaks it, a one-line fix, and a Status field:
Status: active— real defect; orchestrator must decide accept or dismiss in.adversarial-rationale.md.Status: self-dismissed— you concluded inline that this is not actionable (existing pattern, design choice, out-of-scope, false-positive on closer look). MUST include aNote:line with the reason in ≥1 sentence. The orchestrator copies your Note verbatim into the rationale file as**Status:** reviewer-self-dismissed+**Rationale:** (per reviewer) <your Note>.
End your review by calling:
apd_adversarial_pass(total=, accepted=, dismissed=, notes=)
total = findings you raised (active + self-dismissed). accepted = active
findings the builder must act on. dismissed = active findings the builder
can justifiably skip + self-dismissed entries (both counted toward D in
the summary for backward compat; v6.7 rationale file disambiguates them).
If total=0, notes is mandatory (>= 80 chars). Name the categories you
actually examined — regressions, concurrency, edge cases, contract drift,
security surface — and why none surfaced an issue. The server rejects
empty 0/0/0 records to keep this gate honest.
FORBIDDEN
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.
- 10d ago First seen · 77 lines · 18 tokens per session scan A 43298b8f37a0
adversarial-reviewer is an agent published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 744 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
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.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.