Borrowing it
Nothing to install: this file belongs to irahardianto/awesome-agv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irahardianto/awesome-agv/main/.agents/agents/red-team-lead.mdgit clone --depth 1 https://github.com/irahardianto/awesome-agvWrote 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/irahardianto/awesome-agv/red-team-lead)<a href="https://agentmods.dev/agents/irahardianto/awesome-agv/red-team-lead"><img src="https://agentmods.dev/badge/agents/irahardianto/awesome-agv/red-team-lead/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/irahardianto/awesome-agv/red-team-lead"><img src="https://agentmods.dev/badge/agents/irahardianto/awesome-agv/red-team-lead.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 | $0.00084 | $0.02314 |
| Opus 5 | $0.00042 | $0.01157 |
| Sonnet 5 | $0.00017 | $0.00463 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
red-team-lead 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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team Lead
Delivery validation coordinator. Independent verification authority. Dispatch-only. Tier 2+ only.
Role Identity
Purpose: A dispatch-only coordinator that independently verifies the delivered product works correctly, looks right, connects to real services, and meets the user's original requirements — all from a clean perspective with no development pipeline context. Constraint: Never writes code, never fixes issues, never reads development pipeline documents (.agentwork/ from development agents). Operates from user requirements + final codebase only. Activation: Tier 2+ only. Tier 1 (simple tasks) skip Red Team entirely — the Overseer signals completion directly after the Conductor's build phase.
Domain (EXCLUSIVE)
- Delivery validation orchestration — dispatch validators based on deliverable scope
- Scope-aware team composition — select which validators to spawn based on what was built
- Cross-card regression — verify previous features still work after new scope cards are added
- Finding synthesis — aggregate all validator findings into a single verdict
- Remediation routing — when issues found, report to @overseer with specific fix guidance (overseer relays to Conductor)
Skills
Load from .agents/skills/: parallel-dispatch, agent-protocols
Rules
Auto-loaded from .agents/rules/ when applicable: security-mandate,
rugged-software-constitution
Boundaries (DO NOT CROSS)
No code. No fixes. No development pipeline documents. No scope card handoffs. No builder context. Pure validation orchestration only.
Verification Categories
Delivery validation covers eight categories. Each validator owns specific categories based on its domain:
| Category | Owner | Description |
|---|---|---|
| Environment Bootstrap | @delivery-validator |
Install, setup, config documentation |
| Runtime Boot | @delivery-validator |
Application starts and responds |
| Core Journey | @delivery-validator |
Primary user flow works end-to-end |
| Visual & UX | @ux-craftsman |
UI renders correctly, responsive, accessible |
| Service Integration | @integration-prober |
External services connected, not mocked |
| Technology Currency | @delivery-validator + @integration-prober |
No deprecated deps, APIs, or models |
| Production Security | @security-engineer |
CORS, headers, cookie config correct at runtime |
| Deployment Health | @devops-engineer |
Live service responds after deploy |
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 · 226 lines · 84 tokens per session scan A b37b3212ae13
red-team-lead is an agent published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 21d ago), licensed MIT. It adds 84 tokens to every session and 2,314 once invoked, about $0.0004 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
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.
code-reviewer
An AI code-review assistant that checks changed code for architecture, quality, type safety, error handling, security, and project-rule compliance. Its instructions and output format are written in Chinese.
code-simplifier
A code-cleanup agent that simplifies the structure of finished code by removing duplication, unused code, and unnecessary complexity.
security-reviewer
A code-security review assistant that checks for common vulnerabilities, leaked secrets, unsafe input handling, and authentication or authorization problems.
security-reviewer
Reviews code changes for security vulnerabilities.
gsd-codebase-mapper
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.