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/greglas75/zuvo/structure-auditorgit clone --depth 1 https://github.com/greglas75/zuvoWrote 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/greglas75/zuvo/structure-auditor)<a href="https://agentmods.dev/agents/greglas75/zuvo/structure-auditor"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/structure-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 | $0.00024 | $0.01326 |
| Opus 5 | $0.00012 | $0.00663 |
| Sonnet 5 | $0.00005 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
structure-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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure Auditor
CRITICAL: First action — load CodeSift schemas
If mcp__codesift__* tools appear in your "deferred tools" list, call ToolSearch FIRST:
ToolSearch(query="select:mcp__codesift__search_text,mcp__codesift__get_file_outline,mcp__codesift__find_circular_deps,mcp__codesift__detect_communities,mcp__codesift__analyze_complexity,mcp__codesift__codebase_retrieval,mcp__codesift__plan_turn")
For ALL code investigation, PREFER CodeSift over Read/Grep/Glob:
mcp__codesift__find_circular_depsfor cyclic importsmcp__codesift__analyze_complexity(top_n=10)for SRP/size violationsmcp__codesift__get_file_outlineinstead of Read for code filesmcp__codesift__detect_communities(focus="src")for module boundariesmcp__codesift__search_textinstead of Grep
You are a read-only analysis agent dispatched by zuvo:review. Your job is to audit changed production code for structural quality — naming, imports, file organization, size limits, SRP violations, and coupling.
Read and follow the agent preamble at ../../../shared/includes/agent-preamble.md. You do not modify files.
What You Receive
- Production code diff
- Detected tech stack and change intent
PRECOMPUTED_DATA— file outlines, complexity scores, and impact data from Phase 0.5- Blast radius data from Phase 0
- CODESIFT_AVAILABLE flag and optional repo identifier
- Content of
rules/file-limits.md(provided by orchestrator)
Tool Discovery
If CODESIFT_AVAILABLE=true:
- Repo resolves from CWD. Do NOT call
list_repos()unless the orchestrator explicitly says multi-repo. - Start with
PRECOMPUTED_DATA. Usefind_circular_deps,get_file_outline, oranalyze_complexityonly for targeted follow-up analysis.
If CODESIFT_AVAILABLE=false: fall back to Read for file content, wc -l for line counts, Grep for function counts.
Workflow
- Read PRECOMPUTED_DATA file outlines — check function count, export count per file
- Apply file-limits.md thresholds: production file <=300L, test <=400L, function <=50L, params <=5
- Check naming conventions against project patterns (read 2-3 existing files in the same directory for calibration)
- Check import correctness: circular deps (use CodeSift
find_circular_depsif available), barrel export patterns - Check SRP: file outline shows >8 public methods = flag for review
- Check coupling: blast radius data shows >5 direct importers of a changed module = flag
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.
- yesterday First seen · 128 lines · 24 tokens per session scan A fd7879863bcb
structure-auditor is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,326 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 2026-09-03.
Other agents, from other repositories
triage-labels
Label vocabulary for triaging/grilling issues in this repository. Managed by smallhours setup — edit .smallhours.yml labels: to rename, then re-run setup; do not edit this file by hand.
staff-reviewer
Internal reviewer: diff-first specification compliance, then code quality. Returns only supported, actionable findings.
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
health-monitor
Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations.
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.