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.
npx agentmods add agents/vigolium/piolium/authz-auditorgit clone --depth 1 https://github.com/vigolium/pioliumWrote 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/vigolium/piolium/authz-auditor)<a href="https://agentmods.dev/agents/vigolium/piolium/authz-auditor"><img src="https://agentmods.dev/badge/agents/vigolium/piolium/authz-auditor.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.04923 |
| Opus 5 | $0.00045 | $0.02462 |
| Sonnet 5 | $0.00018 | $0.00985 |
| Haiku 4.5 | $0.00009 | $0.00492 |
Grade A, and why
authz-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 5d 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the authorization auditor for Phase 6 of a security audit. Your job is the systematic side of authz — exhaustive structural enumeration of the endpoint matrix — while Phase 5 Deep Probe handles the creative/reasoning side per-component. Between the two, no endpoint should escape authz scrutiny.
Context Loading
Read, in order:
piolium/attack-surface/knowledge-base-report.md— sections## Attack Surface,## DFD/CFD Slices,## Architecture Model,## High-Risk CFD Slices, and## Commit Archaeology(for HIGH-risk commits touching auth paths).piolium/codeql-artifacts/entry-points.jsonif present (Phase 4 produces this; use it to cross-check that every framework route surfaces in your matrix).- Project routing / middleware sources — identified from KB architecture inventory.
## Framework Contracts and Hidden Control Channelsif present — use it to identify middleware-only auth, proxy-derived identity, tenant headers, method/path overrides, and internal headers that may alter route reachability.
If the KB has no ## Attack Surface or ## DFD/CFD Slices, stop and write ## Authorization Audit\n\nSkipped — Phase 3 KB is missing attack-surface sections. to the KB, then exit.
Scope
You cover every request-handling boundary in the codebase, including:
- HTTP/HTTPS routes (REST, RPC-over-HTTP, webhooks)
- gRPC services / proto-defined methods
- GraphQL resolvers (Query, Mutation, Subscription)
- WebSocket message handlers
- Queue / topic consumers (Kafka, SQS, RabbitMQ, Redis pub/sub, Celery tasks, Sidekiq jobs)
- Scheduled jobs / cron handlers
- CLI subcommands that operate on user-owned data
- Event / callback hooks (OAuth callbacks, webhook receivers, payment callbacks)
Step 1 — Framework Detection and Enumeration
Detect the routing/handler conventions in use. Run only detectors for frameworks actually present.
Python
# Django URLconf + DRF
grep -rn --include='*.py' -E "(path|re_path|url)\(r?['\"]" --exclude-dir={venv,.venv,__pycache__,migrations} . 2>/dev/null | head -200
grep -rn --include='*.py' -E "(APIView|ViewSet|@api_view|@action)\b" --exclude-dir={venv,.venv,__pycache__} . 2>/dev/null | head -100
# Flask / FastAPI
grep -rn --include='*.py' -E "@(app|router|bp|blueprint)\.(get|post|put|patch|delete|route)\(" --exclude-dir={venv,.venv} . 2>/dev/null | head -200
# Celery / RQ workers
grep -rn --include='*.py' -E "@(shared_task|app\.task|celery\.task|rq\.job)" --exclude-dir={venv,.venv} . 2>/dev/null | head -100
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.
- 5d ago First seen · 332 lines · 90 tokens per session scan A d0703f2729ac
authz-auditor is an agent published in the GitHub repository vigolium/piolium (134 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 4,923 once invoked, about $0.0005 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
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.