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 skills/lindoelio/spec-driven-steroids/quality-gradingnpx skills add lindoelio/spec-driven-steroids --skill quality-gradinggit clone --depth 1 https://github.com/lindoelio/spec-driven-steroidsWrote 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/lindoelio/spec-driven-steroids/quality-grading)<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/quality-grading"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/quality-grading.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 5.1 | $0.00073 | $0.02215 |
| Opus 5 | $0.00036 | $0.01107 |
| Sonnet 5 | $0.00015 | $0.00443 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
quality-grading 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ffmpeg-ops — 86% identical, 632 lines differ
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Grading Skill
Evaluate and improve code, specifications, or design documents across four quality dimensions with calibrated scoring and auto-fix capabilities.
Overview
This skill provides a multi-dimensional quality grading system for any artifact type:
- Code: Implementation files, modules, functions
- Specifications: Requirements documents, README, acceptance criteria
- Designs: Architecture documents, system designs, technical specifications
It supports two invocation modes:
- evaluate: Score the artifact and return structured JSON results
- grade-and-fix: Score the artifact, then auto-fix dimensions scoring below 5, re-grade, and provide final results
The skill targets score 5+ as the quality bar. Auto-fix attempts are limited to 3 per dimension to keep improvements pragmatic and avoid unnecessary complexity.
Invocation
Load this skill when:
- You want quality feedback on code or implementation
- You want quality feedback on design or architecture documents
- You want quality feedback on specifications or requirements
- You want to improve artifacts scoring below 5 automatically
- You need consistent, calibrated quality assessments
Input
artifact: Path to the file, directory, or snippet to grade (required)mode:evaluateorgrade-and-fix(default:evaluate)
Process
- Load artifact: Read the target file, all files in the directory, or parse the snippet
- Detect artifact type: Determine if this is code, a specification, or a design document
- Apply dimension rubrics: Score each of the four dimensions independently, adapting criteria to artifact type
- Use calibration examples: Compare against few-shot examples for consistency
- If grade-and-fix mode and score < 5: Apply targeted auto-fix, re-grade, repeat up to 3 times
- Generate JSON output: Return structured results with scores, justifications, and suggestions
Grading Dimensions
1. Design Quality
Measures: Architecture clarity, scalability, and separation of concerns
What ships with it
12 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/craft/score-3.md 838 B
- references/craft/score-4.md 1.6 KB
- references/design-quality/score-3-spec.md 588 B
- references/design-quality/score-3.md 793 B
- references/design-quality/score-4-design.md 997 B
- references/design-quality/score-4.md 1.5 KB
- references/functionality/score-3-spec.md 728 B
- references/functionality/score-3.md 968 B
- references/functionality/score-4.md 2.2 KB
- references/originality/score-3-spec.md 786 B
- references/originality/score-3.md 947 B
- references/originality/score-4.md 1.6 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.
- 6d ago First seen · 271 lines · 73 tokens per session scan A 5e2683c1ba76
quality-grading is a skill published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 27d ago), licensed MIT. It adds 73 tokens to every session and 2,215 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
artifact-conventions
Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.
plan-authoring
Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
adr-authoring
Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.