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 skills add krokoko/cairn --skill detect-ai-smellsgit clone --depth 1 https://github.com/krokoko/cairnWrote 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/skills/krokoko/cairn/detect-ai-smells)<a href="https://agentmods.dev/skills/krokoko/cairn/detect-ai-smells"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/detect-ai-smells/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/skills/krokoko/cairn/detect-ai-smells"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/detect-ai-smells.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 | $0.00073 | $0.02185 |
| Opus 5 | $0.00036 | $0.01092 |
| Sonnet 5 | $0.00015 | $0.00437 |
| Haiku 4.5 | $0.00007 | $0.00218 |
Grade A, and why
detect-ai-smells 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess AI Smell Detection Gates
Assess whether a codebase has gates in place to catch AI-generated code smells — patterns indicating output was produced for plausibility rather than understanding. Produce an ai-smells-gates-report.md with coverage of the 11 AI smell categories, gap analysis, recommendations for missing gates, and human review heuristics for what automation can't catch.
Workflow
Step 1: Load smell taxonomy
Load references/ai-smells-taxonomy.md for the 11 AI smell categories and their detection approaches.
These are the categories of AI-generated quality problems the codebase should be protected against:
- Plausible Fabrication
- Cargo-Cult Patterns
- Architecture Astronaut
- Shallow Error Handling (including silent success masking and missing boundary validation)
- Tests Mirroring Implementation
- Symmetry Without Substance
- Local Reasoning Violations (including hard-coded magic values)
- Implicit Drift (unpinned references that silently resolve differently over time)
- Happy-Path-Only Coverage (success path tested; error/edge/boundary paths unexercised)
- Vacuous Tests (tests that execute code but verify nothing falsifiable)
- Vacuous Formal Specs (formal specs, invariants, or gate configs that constrain nothing)
Step 2: Inventory existing gates
Search for mechanisms that would catch AI smells:
Static analysis rules:
- Custom semgrep rules:
.semgrep/,semgrep.yml, semgrep configs in CI - Custom lint rules: eslint plugins, ruff extensions, custom clippy lints
- Complexity checkers: cognitive complexity limits, import depth limits
- Architecture enforcement: dependency-cruiser, ArchUnit, deptry, import-linter
CI quality gates:
- Test coverage thresholds that would catch "tests mirroring implementation" (mutation testing is stronger signal)
- Mutation testing:
stryker,mutmut,cargo-mutants(catches AI005 — tests mirroring implementation) - Dead code detection:
knip,ts-prune,vulture(catches AI002/AI003 — unnecessary abstractions) - Duplication detection:
jscpd,cpd,dupfinder(catches AI006 — symmetry without substance)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ai-smells-gates-report-template.md 2.2 KB
- references/ai-smells-taxonomy.md 10.0 KB
- references/ci-integration.md 3.5 KB
- references/detection-patterns-gates-formal.md 2.2 KB
- references/detection-patterns-gates.md 7.0 KB
- references/detection-patterns.md 3.4 KB
- references/git-history-signals.md 2.5 KB
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 · 161 lines · 73 tokens per session scan A 6d8e181e705d
detect-ai-smells is a skill published in the GitHub repository krokoko/cairn (14 stars, last pushed 5d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,185 once invoked, about $0.0004 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 skills, from other repositories
cleanup-audit
Audit codebase for dead code, unused exports, orphaned files, and stale manifests.
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
reproducibility-validate
Run a workflow multiple times and compare outputs to produce a similarity score and pass/fail verdict.
eval-agent
Run evaluation tests against an agent to assess quality and archetype resistance.
eval-workflow
Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance.
auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern.