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 livlign/claude-skills --skill repo-visuals-retrogit clone --depth 1 https://github.com/livlign/claude-skillsWrote 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/livlign/claude-skills/repo-visuals-retro)<a href="https://agentmods.dev/skills/livlign/claude-skills/repo-visuals-retro"><img src="https://agentmods.dev/badge/skills/livlign/claude-skills/repo-visuals-retro/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/livlign/claude-skills/repo-visuals-retro"><img src="https://agentmods.dev/badge/skills/livlign/claude-skills/repo-visuals-retro.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 | $0.00095 | $0.00960 |
| Opus 5.5 | $0.00038 | $0.00384 |
| Sonnet 5.5 | $0.00019 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
repo-visuals-retro 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-visuals-retro
The repo-visuals skill scores every run on five criteria (see repo-visuals/SKILL.md §6). This meta-skill turns that accumulated evidence into skill improvements.
When to invoke
- You have ≥ 5 runs logged in
./evaluations/runs/in the user's working directory (before that, the sample is noise). - Something feels off across multiple runs and you want a structured look.
- A major change to
repo-visualsis planned and you want the evidence base first.
Do not run this every session. Retros are more valuable with accumulated samples.
Inputs
- The
repo-visualsskill'sSKILL.md— the current skill definition (sibling skill in the same plugin) ./evaluations/index.mdin the user's working directory — curated aggregate from previous retros./evaluations/runs/*.mdin the user's working directory — all per-run raw evaluations since the last retro- Available expert skills in the environment (detected, not assumed)
Workflow
1. Read & tabulate
Read all inputs. Build a small table:
- Average score per criterion, overall and by repo-type bucket (CLI, library, web-app, etc. — infer from scan metadata in each run)
- Variance per criterion (high variance = the skill is inconsistent on that axis)
- Free-text feedback clustered by theme
2. Identify patterns
Name each pattern concretely:
- "Hero moment delivery averaged 2.6 / 5 across the 4 CLI-tool runs but 4.2 / 5 across library runs"
- "Technical polish dropped whenever the stage was < 400 px tall — type legibility likely"
- "3 runs had identical user feedback: 'loop seam is jarring'"
3. Consult expert skills
For each pattern, consult the relevant expert skill(s) if available in the environment. Examples:
- Visual / design critique →
frontend-designskill. Feed it the final HTML + screenshots from low-scoring runs; ask for specific design-rule violations. - Skill structure / prompt design →
skill-creatorskill. Ask whether the skill's Phase N language is ambiguous or missing a step. - Evaluation methodology → any
evaluate-pluginsstyle skill. Ask whether the 5-criterion scorecard is well-calibrated. - Domain-specific knowledge → e.g. an ast-graph / codebase-compare skill if patterns suggest weaknesses in the scan phase.
What ships with it
1 file 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.
- 1mo ago First seen · 87 lines · 95 tokens per session scan A 9be7b9ab9ce5
repo-visuals-retro is a skill published in the GitHub repository livlign/claude-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 95 tokens to every session and 960 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 2026-08-30.
Other skills, from other repositories
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.