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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/full-audit)<a href="https://agentmods.dev/commands/sigistry/marketplace/full-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/full-audit/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/commands/sigistry/marketplace/full-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/full-audit.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 | $0.00013 | $0.00746 |
| Opus 5 | $0.00006 | $0.00373 |
| Sonnet 5 | $0.00003 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
full-audit 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 8d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute a full codebase audit by running all code-auditor analysis agents concurrently.
Process
Step 1: Detect Technology Stack
Before dispatching agents, quickly identify:
- Primary language(s) by scanning file extensions
- Framework(s) by checking package manifests (package.json, pom.xml, build.gradle, requirements.txt, go.mod, Cargo.toml, Gemfile, *.csproj, etc.)
- Project structure pattern (monolith, microservices, monorepo)
Report the detected stack to the user before proceeding.
Step 2: Dispatch Analysis Agents
Launch ALL 5 agents in parallel using the Agent tool. Each agent works independently on its domain:
- security-scanner: Scans for vulnerabilities, hardcoded secrets, injection risks, dependency CVEs
- code-quality-analyzer: Measures code quality, smells, complexity, duplication, standards
- architecture-analyzer: Discovers architecture, maps dependencies, generates diagrams
- performance-analyzer: Identifies bottlenecks, memory leaks, optimization opportunities
- test-coverage-analyzer: Evaluates test coverage, quality, distribution, and gaps
Each agent should be given context about the detected tech stack.
Step 3: Compile Results
After all agents complete, compile their findings into a unified report:
- Present each agent's findings under its own section
- Cross-reference findings (e.g., untested security-critical code, performance issues in complex modules)
- Identify overlapping concerns across domains
Step 4: Generate Final Score
Using the assessment-scoring methodology, calculate the weighted composite score:
| Category | Score | Weight | Weighted |
|---|---|---|---|
| Code Quality | X/10 | 25% | X.XX |
| Performance | X/10 | 25% | X.XX |
| Security | X/10 | 20% | X.XX |
| Maintainability | X/10 | 20% | X.XX |
| Testing | X/10 | 10% | X.XX |
| Total | 100% | X.XX/10 |
Score interpretation:
- 0-2: Critical: Immediate intervention required
- 2-4: Poor: Significant issues affecting development
- 4-6: Fair: Notable issues but manageable
- 6-8: Good: Minor issues, well-maintained
- 8-10: Excellent: Industry best practices
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.
- 8d ago First seen · 88 lines · 13 tokens per session scan A 9c5fe7eda514
full-audit is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 746 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 2026-08-31.
Other commands, from other repositories
review
Multi-agent code review with parallel validation.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
dead-code-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.