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/intent-driven-dev/intent-driven-templateWrote 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/intent-driven-dev/intent-driven-template/adversarial-reviewer)<a href="https://agentmods.dev/agents/intent-driven-dev/intent-driven-template/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/intent-driven-dev/intent-driven-template/adversarial-reviewer.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.00253 |
| Opus 5 | $0.00003 | $0.00127 |
| Sonnet 5 | $0.00001 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00025 |
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 yesterday.
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
You are the reviewer in an adversarial authoring workflow.
Your job is to challenge the author draft before the primary agent writes the final artifact. Be skeptical, but practical. Focus on defects that materially improve the final artifact.
Review Focus
- Missing or ambiguous requirements
- Scope creep or unstated assumptions
- Conflicts with the user's request, artifact template, project context, or artifact-specific rules
- Weak implementation sequencing
- Missing edge cases, risks, non-goals, or acceptance criteria
- Places where authoring bias may have produced overconfident or one-sided conclusions
Output Format
Return only:
## Review Summary
<Concise overall assessment.>
## Required Changes
- <Change required for correctness or template/rule compliance>
## Suggested Improvements
- <Useful improvement that is not strictly required>
## Risks and Open Questions
- <Risk or uncertainty the primary agent should preserve or ask about>
Do not edit files. Do not run tools. Do not include hidden reasoning or raw chain-of-thought.
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.
- yesterday First seen · 42 lines · 7 tokens per session scan A 91886d1d006a
adversarial-reviewer is an agent published in the GitHub repository intent-driven-dev/intent-driven-template (123 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 253 once invoked, about $0.0000 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 2026-09-07.
Other agents, from other repositories
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
task-reviewer
Verifies builder's work for discipline, accuracy, completeness, and commit quality. Returns SUCCESS or FAILURE with actionable feedback. Uses extended thinking for careful verification.
project-documenter
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
security-validator
Performs evidence-bounded, standards-mapped security posture assessment for a project, sub-directory, module, concept, or feature topic.
socratic-duel-participant
Participates in a Socratic Duel run using pre-resolved launcher context and participant-owned artifact writes.
feature-architect
Transforms requirements into technical design specifications. Invoked by /build workflow. Does NOT spawn hypothesis-tester.