redteam

redteam is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 19 tokens per session (4,012 once invoked), scanned A, original, Apache-2.0.

A red-team validation command that checks a software project against its user-flow requirements from a user's perspective. Red-team testing means deliberately looking for failures, missing behavior, and gaps.

In plain words
What is it for?
Use it to validate workspace behavior, review requirements coverage, classify findings, and iterate on fixes.
Why use it?
It helps find problems after implementation and sends actionable findings back for fixing before the project is considered complete.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Good fit Use it to validate workspace behavior, review requirements coverage, classify findings, and iterate on fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/redteam
Install

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.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py

Made for: Claude Code.

Wrote 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.

agentmods badge for redteam

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/redteam/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/redteam)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/redteam"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/redteam/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.

agentmods 80×15 button for redteam

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/redteam"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.04012
Opus 5 $0.00010 $0.02006
Sonnet 5 $0.00004 $0.00802
Haiku 4.5 $0.00002 $0.00401

Measured 9d ago against content hash 8add12aef61a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

redteam 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 9d 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.

.claude/commands/redteam.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Resolution

  1. If $ARGUMENTS specifies a project name, use workspaces/$ARGUMENTS/
  2. Otherwise, use the most recently modified directory under workspaces/ (excluding instructions/)
  3. If no workspace exists, ask the user to create one first
  4. Read all files in workspaces/<project>/briefs/ for user context

Phase Check

  • Verify todos/active/ is empty (all implemented) or note remaining items
  • Read workspaces/<project>/03-user-flows/ for validation criteria
  • Validation results go into workspaces/<project>/04-validate/
  • If gaps are found, document them and feed back to implementation (use /implement to fix)

Execution Model

Autonomous execution model (see rules/autonomous-execution.md). Red team converges through iterative rounds. BUG and INVEST-NOW findings are fixed autonomously to convergence; INCREMENTAL-IMPROVEMENT findings are dispositioned to the deferred-quality tracking list (§ Category-Based Finding Triage below), not ground to convergence. Every dispatched reviewer still RUNS every round — the errored/empty-reviewer evidence gate (Convergence Criterion 3) is unchanged; only the DISPOSITION of findings is triaged by category, never the depth of review.

Conformance Walk is /redteam's primary standing gate — it front-loads the deterministic half (judge every unit, structural-BLOCK the irrefutable failures, hand the human the pre-computed semantic-ADVISORY worklist); it does NOT replace this adversarial round. See skills/conformance-walk/SKILL.md § "Phase-action triggers" (redteam) + § "CW vs /redteam".

Workflow

0. Posture-aware audit DEPTH — convergence is NOT posture-gated (MUST consult first)

Read .claude/learning/posture.json via state-io.js::readPosture. /redteam MUST run to convergence — every invocation at L2–L5 runs to 2 consecutive clean rounds + Convergence Criteria 4–6 below; convergence is the posture-INVARIANT target. Posture scales only the per-round DEPTH floor (WHAT each round checks), never WHETHER convergence is reached. Depth is cumulative down the ladder (skills/32-trust-posture/redteam-integration.md):

Read the full file on GitHub · 158 lines

Changes

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.

  1. 9d ago First seen · 158 lines · 19 tokens per session scan A 8add12aef61a

Subscribe to this mod's changes

redteam is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 19 tokens to every session and 4,012 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 2026-09-03.