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-level-simulatornpx skills add trycomp-io/comp-skills --skill comp-level-simulatorgit 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 | $0.00186 | $0.02353 |
| Opus 5 | $0.00093 | $0.01177 |
| Sonnet 5 | $0.00037 | $0.00471 |
| Haiku 4.5 | $0.00019 | $0.00235 |
Grade A, and why
comp-level-simulator 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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-mode operation (Code + Cowork)
HTML through the design system (required). Whenever this skill produces HTML, load the
comp-html-guidelinesskill first and apply the CompDS design system. This holds even when the user does not ask to "style it" or "make it look good" — every HTML output from this skill goes through the design system. It does not change the methodology below; it only governs the HTML's visual layer.
Detect platform at start:
- If you have the
Bashtool AND can run Python → use script mode (generates the interactive standalone HTML). Existing workflow below. - Otherwise (e.g., Claude Cowork) → use inline mode: conduct the assessment conversationally per the "Inline assessment logic" section, compute the score in chat, present a markdown scorecard. If an HTML artifact tool is available, ALSO render a self-contained HTML result (Tailwind CDN) matching the script's output.
Inline assessment logic (Cowork mode)
Avalie 1 cargo por vez. 4 pilares, 2 perguntas cada (8 perguntas). Cada pergunta usa a mesma escala A–E.
Escala por pergunta (mesma pra todas):
| Opção | Score | Significado |
|---|---|---|
| A | 5 | Sempre / 100% / Grande escala |
| B | 4 | Frequentemente / ~75% / Escala moderada |
| C | 3 | Ocasionalmente / ~50% / Pequena escala |
| D | 2 | Raramente / ~25% / Muito pouco |
| E | 1 | Nunca / 0% / Não se aplica |
Pilares e perguntas (texto exato):
- Influência: impacto nas decisões e estratégias
- Q1: O trabalho do indivíduo impacta as decisões e estratégias em toda a empresa?
- Q2: O indivíduo pode iniciar e liderar mudanças em todo o departamento sem aprovação prévia?
- Autonomia: capacidade de agir sem supervisão
- Q3: O indivíduo trabalha sem supervisão?
- Q4: O indivíduo pode definir suas próprias metas e prazos?
- Complexidade: análise e resolução de problemas
- Q5: O trabalho do indivíduo envolve lidar com projetos interdepartamentais?
- Q6: O indivíduo é responsável por resolver problemas complexos que afetam os resultados do negócio?
- Responsabilidade: obrigações por pessoas, resultados e recursos
- Q7: O indivíduo é responsável por gerenciar um orçamento ou recursos?
- Q8: O papel do indivíduo envolve liderar equipes ou projetos?
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.
- 3d ago First seen · 168 lines · 186 tokens per session scan A ca49264dc887
comp-level-simulator is a skill published in the GitHub repository trycomp-io/comp-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 186 tokens to every session and 2,353 once invoked, about $0.0009 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.
biome
Repository guidance for using Biome as the formatter, linter, and code quality tool within the hr-skills monorepo.
resume-screener
简历筛选与评分系统的实现参考。LLM 评 4 维度最终分（exp/skill/proj/major）+ 脚本查 schooltier 校准 edu + 公式重算 total。 本 Skill 不是工作流入口。通用智能体应只通过 boss-hr-auto → 统一 CLI boss-hr score 调用。 本文档保留作为：评分规则参考 / LLM 提示词片段来源 / 算法实现文档。 唯一方案：5 维度 weighted 求和（edu 25% / exp 25% / skill 25% / proj 15% / major 10%），Tier 阈值 ≥70 推荐 / 60-69 待定 / <60 不推荐。.