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/ANcpLua/ancplua-claude-pluginsWrote 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/commands/ancplua/ancplua-claude-plugins/red-blue-review)<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/red-blue-review"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/red-blue-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/commands/ancplua/ancplua-claude-plugins/red-blue-review"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/red-blue-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 | $0.00040 | $0.02081 |
| Opus 5.5 | $0.00016 | $0.00832 |
| Sonnet 5.5 | $0.00008 | $0.00416 |
| Haiku 4.5 | $0.00004 | $0.00208 |
Grade A, and why
red-blue-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 14d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RED BLUE REVIEW — Adversarial Attack/Defense with Scoring
Red breaks. Blue fixes. Red re-attacks. Points decide.
Target: $0 (default: staged changes) Scope: $1 (default: full | full|security|api|performance)
SCORING
| Event | Red | Blue |
|---|---|---|
| Valid critical finding | +10 | — |
| Valid high finding | +5 | — |
| Valid medium finding | +2 | — |
| Invalid/false finding | -5 | — |
| Fix verified (no bypass) | — | +5 |
| Fix bypassed by Red | +3 | -3 |
| Test case accepted | — | +2 |
TEAM ARCHITECTURE
REVIEW LEAD (You — Orchestrator)
│
│ TeamCreate: "red-blue-review"
│
├─ Phase 1: RED ATTACK (3 teammates, coordinate via SendMessage)
│ ├── red-crash-hunter ──────┐
│ ├── red-security-attacker ─┼── SendMessage: share attack vectors
│ └── red-api-breaker ───────┘ TaskCreate: each finding → shared list
│ └── GATE → validate findings, shutdown_request → Red
│
├─ Phase 2: BLUE DEFENSE (1 teammate per MODULE)
│ └── blue-defender-N ── TaskUpdate: claim findings, SendMessage: cross-module fixes
│ └── GATE → fixes collected, shutdown_request → Blue
│
├─ Phase 3: RED RE-ATTACK (1 teammate per module)
│ └── red-reattacker-N ── TaskUpdate: DEFEATED/BYPASSED/INCOMPLETE
│ └── shutdown_request → re-attackers
│
├─ RELEASE: SAFE / BLOCK
└─ TeamDelete
<CRITICAL_EXECUTION_REQUIREMENT>
STEP -1 — Inherit Prior Findings:
If <EXODIA_FINDINGS_CONTEXT> tag exists in session context, read .eight-gates/artifacts/findings.json.
Inject findings into Red Team prompts as attack surface hints. Do NOT give to Blue — they defend blind.
THIS IS AN ADVERSARIAL EXERCISE.
STEP 0 — Create Team: TeamCreate: team_name = "red-blue-review", description = "Adversarial review: $0"
STEP 1 — Red Attack Phase: Spawn 3 Red attackers as teammates (ALL in ONE message): Task tool: team_name="red-blue-review", name="red-crash-hunter", subagent_type="general-purpose", model="opus" Task tool: team_name="red-blue-review", name="red-security-attacker", subagent_type="general-purpose", model="opus" Task tool: team_name="red-blue-review", name="red-api-breaker", subagent_type="general-purpose", model="opus"
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.
- 14d ago First seen · 212 lines · 40 tokens per session scan A 738ce8efccef
red-blue-review is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 2,081 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.