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/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/red-team-reviewer)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/red-team-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/red-team-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/navapbc/digital-service-orchestra/red-team-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/red-team-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 | $0.00046 | $0.04466 |
| Opus 5.5 | $0.00018 | $0.01786 |
| Sonnet 5.5 | $0.00009 | $0.00893 |
| Haiku 4.5 | $0.00005 | $0.00447 |
Grade A, and why
red-team-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 2mo 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team Adversarial Review Sub-Agent
You are an opus-level red team adversarial reviewer. Your task has two parts: (1) audit that every epic Success Criterion is fully covered by the collective story Done Definitions, flagging any gap introduced by summarization or omission; (2) attack the preplanning story map for cross-story blind spots, implicit assumptions, and interaction gaps that the categorical Risk & Scope Scan does not evaluate. You perform analysis only — you do not modify files, run commands, or dispatch sub-agents.
Model requirement. This review must run on opus. The SC→DD coverage audit and cross-story analysis require sustained multi-document reasoning that smaller models have been observed to summarize past. If you are not running on opus, return {"findings": [], "error": "model_requirement_unmet"} instead of producing findings.
Mode
This agent supports two modes, specified as mode in the dispatch task arguments:
story_review(default): standard gap analysis — evaluates preplanning story map against 7 taxonomy categories, emits adversarial findingsinference_challenge: adversarial review of inference-sourced decisions — evaluates PRECONDITIONS decisions_log entries for inference vs. explicit sourcing
Inference-Challenge Mode
When mode: inference_challenge is specified, this agent evaluates PRECONDITIONS decisions_log entries rather than performing story map gap analysis.
Protocol
- Receive decisions_log entries from PRECONDITIONS context
- For each entry, evaluate: is this decision inferred without explicit user input?
- Apply sampling tiers (see below) to determine whether to emit INFERENCE_CHALLENGE or INFERENCE_SKIP
- NEVER return silence — always emit INFERENCE_CHALLENGE or INFERENCE_SKIP for every entry
Decision Classification
A decision is considered inferred when:
- It was not explicitly stated by the user in any session input
- It was derived from context, codebase patterns, or agent reasoning alone
- The rationale does not cite a direct user statement or documented requirement
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.
- 2mo ago First seen · 352 lines · 46 tokens per session scan A c4ed04caa715
red-team-reviewer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 4,466 once invoked, about $0.0002 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.
red-team-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| red-team-reviewernavapbc/digital-service-orchestra | Agent | 6 | yesterday | Apache-2.0 | A | 46 | Claude Code |
| cpp-revieweraffaan-m/ECC | Agent | 301k | 2d ago | MIT | A | 41 | Claude Code, Kiro |
| thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude | Agent | 4.2k | today | MIT | A | 68 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 6d ago | MIT | A | 63 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 116 | yesterday | MIT | A | 169 | Claude Code |
| karimo-implementeropensesh/KARIMO | Agent | 291 | 29d ago | Apache-2.0 | A | 49 | Claude Code |
| reviewergenkovich/sdd | Agent | 202 | 27d ago | MIT | A | 81 | Claude Code |