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/trycomp-io/comp-skills/comp-html-guidelinesnpx skills add trycomp-io/comp-skills --skill comp-html-guidelinesgit clone --depth 1 https://github.com/trycomp-io/comp-skillsWhat 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 | $0.00149 | $0.01100 |
| Opus 5 | $0.00075 | $0.00550 |
| Sonnet 5 | $0.00030 | $0.00220 |
| Haiku 4.5 | $0.00015 | $0.00110 |
Grade A, and why
comp-html-guidelines 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comp HTML Guidelines
A lightweight, self-contained visual style guide for every HTML report, page, dashboard, or analysis produced by a Comp skill. Load it whenever you are about to write or restyle HTML so the result is consistent, polished, and on-brand. It does not change the methodology of the calling skill, it governs only the visual layer.
This is a Knowledge skill. The full rules live in references/style-guide.md and a ready-to-inline stylesheet lives in assets/comp-base.css. Read the style guide before writing HTML.
When to use
- Generate — creating a new HTML report from scratch. Load
references/style-guide.md, inlineassets/comp-base.css, then build. - Apply — the user has existing HTML and wants it styled ("estiliza", "padroniza", "deixa isso bonito", "apply the design"). Load the style guide and re-skin the markup, keeping the content.
- Consult — a question about a specific rule (color, layout, footer, chart). Answer from
references/style-guide.md.
The look in one paragraph
Near-white background (#FAFAF8), content in white cards with a hairline border and soft radius. Comp black (#1F1B17) for text and the hero, Comp red (#F4364C) as the single accent. DM Sans for everything. Generous spacing (24px rhythm). A hero band at the top with the report title and a short subtitle; a "Powered by Comp" footer at the bottom. One accent color only, semantic green/amber/red reserved for good/warning/bad states. No gradients, no decorative icons, no rainbow palettes.
How to build
- Read
references/style-guide.mdin full. - Start from the base scaffold in the style guide and inline
assets/comp-base.cssinside a<style>tag (copy it, do not link to a CDN for it). - Load DM Sans from Google Fonts and a charting library (Chart.js) from a CDN if you need charts.
- Build the hero, then the content as cards / tables / stat cards, then the footer.
- Run the self-review checklist at the end of the style guide before delivering.
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.
- 2d ago First seen · 51 lines · 149 tokens per session scan A 05c59b2f5dae
comp-html-guidelines is a skill published in the GitHub repository trycomp-io/comp-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 1,100 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
hr-root-router-maintaining
Maintenance guide for the root SKILL.md router in the hr-skills monorepo. Use this skill when adding a new HR skill package, removing a deprecated skill, renaming a skill directory, moving a skill between routing sections, or auditing the router for consistency with the actual skills/ directory.
hr-skills-maintaining
Repository-level skill describing metadata, directory structure, workflows, and conventions for the hr-skills monorepo. Use this skill when validating, creating, editing, or maintaining HR skill packages, including SKILL.md, content/, prompts/, and examples/.
github-awesome-copilot-git-commit
Generate high-quality, atomic Conventional Commits by analyzing Git changes, recommending logical commit boundaries, validating commit messages, and assisting with PRs, changelogs, and releases.
markdown
Repository guidance for writing, formatting, and validating Markdown documentation using markdownlint-cli, case-police, and markdown-link-check within the hr-skills monorepo.
turbo
Repository guidance for using Turborepo to orchestrate workspace tasks, builds, validation, testing, and development workflows within the hr-skills monorepo.
changeset
Use when determining whether a pull request requires a changeset, selecting the appropriate version bump (patch, minor, or major), or writing a .changeset/.md entry for the hr-skills repository.