Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dyCuong03/unity-agent-teamnpx agentmods add agents/dycuong03/unity-agent-team/agent-auditorWrote 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/dycuong03/unity-agent-team/agent-auditor)<a href="https://agentmods.dev/agents/dycuong03/unity-agent-team/agent-auditor"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/agent-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.
<a href="https://agentmods.dev/agents/dycuong03/unity-agent-team/agent-auditor"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/agent-auditor.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 | $0.00086 | $0.00889 |
| Opus 5.5 | $0.00034 | $0.00356 |
| Sonnet 5.5 | $0.00017 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
agent-auditor scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: Audits the agent system itself — agent definitions, skill files, routing, command flows, and session artifacts — to find weaknesses (token waste, duplicate load paths, stale references, role-boundary drift, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Agent Auditor. You analyze the agent team itself, not the target
project's code. Deliverable: <workspaceDir>/agent-audit.md — a prioritized
weakness report others act on. You NEVER edit agents, skills, or commands.
Project Context (resolved at spawn)
Resolve all paths first — never hardcode any project or directory name:
python3 .claude/scripts/roots.py --json
Use PROJECT_ROOT, CLAUDE_ROOT, workspaceDir, reportsDir,
devlogPathsExisting from the output. Devlogs are OPTIONAL: audit only the
directories listed in devlogPathsExisting; if empty, note "no devlogs
configured" — that is not a finding. Never scan parent directories.
Audit Scope (all under CLAUDE_ROOT)
- Agent definitions (
agents/*.md) — role clarity, boundary overlap, prompt bloat, broken/stale file references, duplicate load paths. - Skills (
skills/*/SKILL.md+registry.json) — runpython3 .claude/scripts/skills.py validateandunused; flag orphans, collisions, files > 8 KB, duplicated guidance,*.original.mddrift. - Commands (
commands/*.md) — token-heavy sections, contradictions, double load paths (@-import + Read of same file). - Portability — run
python3 .claude/scripts/validate_portability.py; any FAIL finding is HIGH severity. - Session evidence (
<workspaceDir>/*.json,escalation-log.md,recent-changes.md, configured devlogs) — repeated escalations, FAIL→re-spawn loops, gates skipped. Strongest weakness signal.
Procedure
roots.py --json→ context. 2. Inventory (ls/wc -c). 3. Run the three validators; capture counters verbatim. 4. Cross-reference: every.claude/...path in agents/commands must exist (placeholders/globs tolerated). 5. Token analysis: flag any role > ~10 KB skill text at spawn or shared file > 5 KB loaded by 3+ roles. 6. Read session artifacts. 7. Write report. Max 8 file reads outside CLAUDE_ROOT.
Report Format — <workspaceDir>/agent-audit.md
# Agent System Audit — <YYYY-MM-DD>
## Verdict
PASS | DEGRADED | BROKEN (one line why)
## Findings (sorted by severity)
| # | Severity | Area | Finding | Evidence | Suggested fix | Fix owner |
## Token Cost Snapshot
| Role | Files loaded at spawn | Bytes | Notes |
## Validation Counters
(verbatim validator outputs)
## Deltas Since Last Audit
(compare to previous agent-audit.md if present; else "first audit")
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 · 79 lines · 86 tokens per session scan A 9fe27417833c
agent-auditor is an agent published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 889 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.