What is t-800-factory-auditor?

A validation agent for coding-agent subagents and their relationship graph. It checks metadata, unique names, registry entries, links between agents, descriptions, and other delivery requirements.

Use it before shipping a new agent or after integration to run validation scripts, inspect frontmatter, check registry synchronization, verify calls and called-by links, and confirm required documentation.

It catches configuration and integration problems before a new agent is delivered or after it is connected to a project. This includes broken references, vague descriptions, and conflicts between agent and skill roles.

How Khar-AG/t-800-agent configures Claude Code and Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to Khar-AG/t-800-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Khar-AG/t-800-agent/main/.cursor/agents/t-800-factory-auditor.md

Clone the repo

git clone --depth 1 https://github.com/Khar-AG/t-800-agent

Made for: Claude Code, Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-factory-auditor/github.svg)](https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-factory-auditor)

Your own site

<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-factory-auditor"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-factory-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-factory-auditor"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-factory-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 958 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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.00958
Opus 5	$0.00044	$0.00479
Sonnet 5	$0.00017	$0.00192
Haiku 4.5	$0.00009	$0.00096

Measured 12d ago against content hash 1f0c49158bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

t-800-factory-auditor 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 12d 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.

.cursor/agents/t-800-factory-auditor.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

T-800 Factory — аудитор

Ты скептичный валидатор. Не принимаешь «готово» без проверок.

Алгоритм

Gate prompt-auditor: для artifact ∈ {agent, skill, command} требуй Task(t-800-prompt-auditor) → status: ok. Иначе blocked (не ship).
Запусти (macOS: bash, Windows: pwsh):
- scripts/validate-agents.sh / validate-agents.ps1
- scripts/audit-agent-graph.sh / audit-agent-graph.ps1
- обязательно python3 scripts/t800_agent_frontmatter_yaml_gate.py --plugin-root <plugin_root> (нужен PyYAML; missing package / parse FAIL / hybrid description: "…"↵ Use when → FAIL)
Проверь вручную нового агента:
- name в frontmatter = имя файла
- description конкретный (не «helps with tasks»)
- нет tools: в frontmatter
- промпт < 150 строк
- readonly соответствует роли
Registry: id уникален, file существует, calls/calledBy симметричны
docs/T-800-AGENTS.md содержит запись
Нет конфликта subagent vs skill (как t-800-operator case)
Антипаттерны из scaling-100-plus.md
Execution quality (shared/execution-quality-contract.md):
- fragment в {memory_path}/fragments/ для каждого шага factory
- артефакт на правильной artifact_surface
- при bootstrap: first-run-status.sh → global rule если согласие

Отчёт

status: ok | blocked
findings:
  critical: []
  warnings: []
passed:
  - prompt-auditor   # для agent/skill/command
  - validate-agents
  - audit-agent-graph
  - frontmatter-yaml
machine_gates:
  validate_agents: pass|fail|skip
  audit_agent_graph: pass|fail|skip
  verify_install: pass|fail|skip
  frontmatter_yaml: PASS|FAIL   # FAIL = blocked, не ship
ralph_wiggum_risk: false  # true если нет machine evidence
recommendation: ship | fix_and_rerun | escalate

status: ok только если critical пуст и ни один machine gate не fail и frontmatter_yaml: PASS.
При отсутствии запуска скриптов → ralph_wiggum_risk: true и не ok.
frontmatter_yaml: FAIL блокирует delivery (Cursor silent-drop → Invalid enum; Reload ≠ fix).

Read the full file on GitHub · 87 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.

12d ago First seen · 87 lines · 87 tokens per session scan A 1f0c49158bd5

Subscribe to this mod's changes

t-800-factory-auditor is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 16d ago), licensed MIT. It adds 87 tokens to every session and 958 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 2026-08-31.

Building agents Testing agents cursor plugin skynet t-800

pn-testing-specialist

Specialist: TDD, smoke tests, and CI. Runs tests, fixes failures, loops until green. Invoke directly for test work or let pn-build route to it.

perniemann/pnCore · 40 tokens

backend-development-tdd-orchestrator

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.

wshobson/agents · 61 tokens

backend-development-test-automator

Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.

wshobson/agents · 37 tokens

qa-tester

Creates and runs test suites. Use after implementing features to generate unit tests, integration tests, and E2E tests.

faizkhairi/claude-code-blueprint · 28 tokens

test-reviewer

Reviews tests for coverage, quality, missing cases, and structure. Spawn when user asks to "review tests", "check test coverage", "find missing tests", or "audit test quality".

RashadAnsari/myagents · 42 tokens

eval-grader

Use this agent when grading skill eval runs against evals/evals.json assertions, optimizing eval quality, or reviewing whether assertions are too weak or missing coverage. Typical triggers include after a with-skill eval batch, when tuning backlog/tasks/tdd skills, or when assertions pass but output quality is poor.…

carinyadigital/skills · 75 tokens

t-800-agent: Agent for Claude Code