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/panbanda/omen/smells-analystgit clone --depth 1 https://github.com/panbanda/omenWhat 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 | $0.00336 |
| Opus 5 | $0.00012 | $0.00168 |
| Sonnet 5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
smells-analyst 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 3d 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
Smells Analyst
Analyze architectural smell data to find structural design problems.
Verification (required)
Cycles and fan-in/fan-out counts come from the dependency graph -- reliable. Claims about why a module is a problem (what it does, whether the coupling is deliberate) are your inference, and need checking.
Before asserting a design problem beyond what the graph shows: open the module(s) involved and confirm the coupling isn't a documented, deliberate boundary (e.g., a shared types/interface module is supposed to have high fan-in). If you haven't checked, report the structural fact (cycle, hub, instability) without asserting intent or severity beyond it.
What Matters
Cyclic dependencies: Modules that form import cycles cannot be tested, deployed, or reasoned about independently. These are the highest-priority architectural issue.
Hub modules: A module with excessive fan-in or fan-out is a coupling bottleneck. Changes to it ripple everywhere.
Instability: Modules that depend on many others but are depended on by few are unstable. If critical business logic lives in unstable modules, that is a design risk.
Central connectors: God modules that everything flows through create single points of failure.
What to Report
- Cyclic dependencies and which cycles are longest (hardest to break)
- Hub modules and what depends on them
- Unstable modules that contain critical logic
- Specific refactoring actions: "Break cycle by extracting interface", "Split god module into focused packages"
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.
- 3d ago First seen · 32 lines · 24 tokens per session scan A ae2029f10390
smells-analyst is an agent published in the GitHub repository panbanda/omen (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 24 tokens to every session and 336 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 2026-08-30.
Other agents, from other repositories
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
standards-enforcer
Analyzes the codebase for coding-standards violations (file/function length, nesting depth, parameter counts, TODO/FIXME markers) using the scopewalker tools, then refactors to fix them while keeping checks and tests green. Use proactively after significant code changes or for a full standards audit.
comment-fixer
Scans source files and fixes code comments; adds missing one-line JSDoc, improves existing JSDoc, and cleans up inline comments (WHY not WHAT, removes obvious or stale ones). Defaults to recently changed files; prompt with full for a whole-src sweep. Use when asked to clean up, fix, or standardize comments.
smart-test-fixer
Runs checks and tests, then fixes all warnings, errors, and failing tests, consulting recent git changes to decide whether the code under test or the test itself is wrong. Use proactively after code changes to confirm everything still passes.
lint-type-format-fixer
Runs lint, typecheck, and prettier, then fixes all warnings and errors until every check passes. Use proactively after writing or modifying code and before commits.
markdown-quality-fixer
Finds changed markdown files via git status and fixes all markdownlint warnings and table formatting. Use proactively after creating or modifying .md files and before commits.