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 rjmurillo/ai-agents --skill quality-gradesgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/quality-grades)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/quality-grades"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/quality-grades/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/rjmurillo/ai-agents/quality-grades"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/quality-grades.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 12 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 12 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00108 | $0.01336 |
| Opus 5.5 | $0.00043 | $0.00534 |
| Sonnet 5.5 | $0.00022 | $0.00267 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
quality-grades 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 22d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Grades
Grade each product domain and architectural layer. Track gaps over time.
Triggers
grade qualityaudit domain qualityshow quality gapsrun quality gradesdomain quality report
Process
- Detect domains:
grade_domains.pyauto-detects product domains from the repo layout (or use--domainsto scope). - Grade layers: each domain is scored A-F across six architectural layers (agents, skills, scripts, tests, docs, workflows), with gaps tagged critical, significant, or minor.
- Report: emit markdown or JSON; with
--output, the script loads prior JSON to compute per-domain trends (improving, stable, degrading, new). - Act: address critical gaps first; rerun to track movement.
Quick Start
# Grade all auto-detected domains
python3 .claude/skills/quality-grades/scripts/grade_domains.py
# Grade specific domains as JSON
python3 .claude/skills/quality-grades/scripts/grade_domains.py --domains security memory --format json
# Write report to file (enables trend tracking)
python3 .claude/skills/quality-grades/scripts/grade_domains.py --output quality-grades.md
# Show top 10 domains by gap count
python3 .claude/skills/quality-grades/scripts/grade_domains.py --top-n 10
Grading Criteria
| Grade | Score | Meaning |
|---|---|---|
| A | 90-100 | Full coverage, no known gaps |
| B | 75-89 | Minor gaps, non-blocking |
| C | 60-74 | Gaps present, should address |
| D | 40-59 | Significant gaps, blocking quality |
| F | 0-39 | Broken or missing |
Architectural Layers
Each domain is graded across six layers:
What ships with it
5 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.
- 22d ago Changed · +6 lines 0284859a3c6b
- 1mo ago First seen · 146 lines · 108 tokens per session scan A 169d96f9077a
quality-grades is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 1,336 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.