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 calionauta/stelow --skill stelow-workflow-codebase-critiquegit clone --depth 1 https://github.com/calionauta/stelowWrote 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/calionauta/stelow/stelow-workflow-codebase-critique)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-workflow-codebase-critique"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-workflow-codebase-critique.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02250 |
| Opus 5 | $0.00047 | $0.01125 |
| Sonnet 5 | $0.00019 | $0.00450 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
stelow-workflow-codebase-critique 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Critique
Focus: Critically analyze source code structure — architecture, data flow, API contracts, performance, theming, responsive patterns, and AI slop in code. Input: Source code directory. Output: Classified gap report (🚨/🤔/🔎) with recommendations.
Tools: See
references/cli-tools/subagents.mdfor subagent patterns.
Standalone awareness: inside stelow, appetite gates critique depth (Lean → light, Core → quick, Complete → full). Standalone defaults to Core appetite (quick single-reviewer). Works with any source directory — no stelow dependency for the audit logic.
Overview
Structural codebase critique — evaluates architecture, data flow, API contracts, performance, theming, responsive patterns, and AI slop in code.
This skill performs a source code audit using checklists focused on technical and structural aspects (non-visual):
| Dimension | What it evaluates |
|---|---|
| 🏗️ Architecture | Module structure, dependency flow, coupling |
| 🔄 Data Flow | Call chains, state management, event propagation |
| 📡 System Contracts | API definitions, error handling, logging |
| ⚡ Performance | Bundle size, re-renders, lazy loading |
| 🎨 Theming | Design tokens, dark mode support |
| 📱 Responsive | CSS breakpoints, media queries |
| 🤖 AI Slop in Code | Over-generated patterns, redundant code, boilerplate |
Important: This skill is for analyzing source code of components and logic.
If you need visual UI auditing (accessibility, design, UX), use
stelow-workflow-ux-critique em Codebase mode.
Appetite Gate (auto-skip for small scopes)
Before running codebase critique, check if appetite warrants it. Codebase critique is for structural analysis — if the scope is 1 file, the value is minimal.
# Read appetite from stelow context or env var; default Core (via canonical helper).
WF_DIR="$(ls -td .stelow/*/*/ 2>/dev/null | head -1)"
# shellcheck disable=SC1091
source "$(dirname "${BASH_SOURCE[0]:-$0}")/../../stelow-workflow-orchestrator/references/cli-tools/read-config.sh"
APPETITE="${APPETITE:-$(stelow_read_appetite)}"
DIFF_FILES=$(git diff --name-only HEAD~1 2>/dev/null | wc -l | tr -d ' ')
What ships with it
3 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.
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 · 238 lines · 94 tokens per session scan A 3ff418b23ce2
stelow-workflow-codebase-critique is a skill published in the GitHub repository calionauta/stelow (10 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 2,250 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…