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/CrashBytes/claude-role-skillsWrote 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/crashbytes/claude-role-skills/legacy-audit)<a href="https://agentmods.dev/commands/crashbytes/claude-role-skills/legacy-audit"><img src="https://agentmods.dev/badge/commands/crashbytes/claude-role-skills/legacy-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/crashbytes/claude-role-skills/legacy-audit"><img src="https://agentmods.dev/badge/commands/crashbytes/claude-role-skills/legacy-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 | $0.00007 | $0.00392 |
| Opus 5 | $0.00003 | $0.00196 |
| Sonnet 5 | $0.00001 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
legacy-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 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.
What it actually says
Legacy System Audit
Audit a codebase to assess modernization readiness and identify migration priorities.
Arguments
Target to audit: $ARGUMENTS
Workflow
-
Inventory the system
- Scan the codebase structure and file types
- Identify languages, frameworks, and their versions
- Map dependency graph (direct and transitive)
- Detect deprecated APIs and end-of-life dependencies
-
Assess code health
- Estimate test coverage (presence and quality of test files)
- Check for documentation (README, API docs, inline comments)
- Identify code smells: god classes, long methods, circular dependencies
- Check for hardcoded configuration, magic numbers, dead code
-
Evaluate architecture
- Monolith vs modular vs microservices
- Coupling analysis: how tightly are components connected?
- Identify natural service boundaries (bounded contexts)
- Database structure: single DB, shared schemas, data ownership
-
Security assessment
- Outdated dependencies with known CVEs
- Authentication and authorization patterns
- Secret management practices
- Input validation and output encoding
-
Score modernization readiness Rate each dimension 1-5:
- Code quality and maintainability
- Test coverage and confidence
- Documentation completeness
- Architecture modularity
- Dependency health
- Security posture
- Team knowledge and skills
-
Output
- System inventory summary
- Health scorecard (radar chart dimensions)
- Top 10 modernization priorities ranked by impact and effort
- Recommended migration approach (based on scores)
- Quick wins that can be done before a full migration
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.
- 9d ago First seen · 57 lines · 7 tokens per session scan A ebf0ce0831d8
legacy-audit is a command published in the GitHub repository CrashBytes/claude-role-skills (6 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 392 once invoked, about $0.0000 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-pr
Review a pull request against an authorized reviewer's brief — answer their questions, examine their angles, run their validations, and converse until they say done. Change NO code.
pr-description
Write a pull request description that helps reviewers: what changed, why, and how to verify, from a diff.
refactor-code
Suggest refactorings that improve readability and structure without changing behavior, ranked by payoff.
resolve-review
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
review-code
Agent review pass plus manual checklist for correctness, security, performance, and accessibility.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.