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 andregusman-raiz/a-gusman-claude --skill markdown-viewergit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/markdown-viewer)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/markdown-viewer"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/markdown-viewer/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/andregusman-raiz/a-gusman-claude/markdown-viewer"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/markdown-viewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 34 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 | $0.00043 | $0.00375 |
| Opus 5.5 | $0.00017 | $0.00150 |
| Sonnet 5.5 | $0.00009 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
markdown-viewer 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.
What it actually says
Markdown Viewer
Use o runtime canônico desta skill; não copie a aplicação para o projeto.
Operação
Resolva o projeto-alvo e execute diretamente:
bash ~/Claude/.claude/skills/markdown-viewer/scripts/markdown-viewer.sh --project <PROJECT_ROOT>
- Validar sem subir servidor: acrescente
--check. - Criar o manifesto seguro padrão quando ele não existir: acrescente
--init, depois revise a allowlist. - A porta padrão é
3006; use--port Nsomente em conflito. - O servidor deve permanecer em
127.0.0.1; nunca exponha com0.0.0.0.
Ao criar ou alterar a allowlist, leia references/manifest.md. Para localhost, siga a regra global: navegação e screenshots via Playwright.
Invariantes
.markdown-viewer.jsoné obrigatório; ausência nunca libera um diretório por fallback.- Não publique
CLAUDE.md,AGENTS.md,docs/ai-state/**,entrada/**,Downloads/**ou formatos não Markdown. - Preserve o manifesto existente; mudanças de escopo documental exigem edição explícita.
- A fonte canônica atende Claude e Codex por
.agents/skills -> .claude/skills; não duplique a skill.
What ships with it
35 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.
- agents/openai.yaml 287 B
- assets/app/.gitignore 78 B
- assets/app/AGENTS.md 678 B
- assets/app/CLAUDE.md 11 B
- assets/app/eslint.config.mjs 344 B runs code
- assets/app/next-env.d.ts 288 B runs code
- assets/app/next.config.ts 177 B runs code
- assets/app/package-lock.json 384 KB
- assets/app/package.json 1.2 KB
- assets/app/playwright.config.ts 722 B runs code
- assets/app/postcss.config.mjs 110 B runs code
- assets/app/scripts/check-project.ts 562 B runs code
- assets/app/scripts/init-project.ts 823 B runs code
- assets/app/src/app/documento/[...slug]/page.tsx 1.3 KB
- assets/app/src/app/error.tsx 427 B
- assets/app/src/app/globals.css 9.2 KB
- assets/app/src/app/layout.tsx 931 B
- assets/app/src/app/not-found.tsx 556 B
- assets/app/src/app/page.tsx 1.3 KB
- assets/app/src/components/document-shell.test.tsx 3.6 KB
- assets/app/src/components/document-shell.tsx 5.7 KB
- assets/app/src/components/markdown-view.tsx 1.2 KB
- assets/app/src/components/viewer-states.tsx 1.6 KB
- assets/app/src/lib/document-access.test.ts 4.4 KB runs code
- assets/app/src/lib/document-manifest.ts 2.7 KB runs code
- assets/app/src/lib/document-path.ts 2.1 KB runs code
- assets/app/src/lib/document-reader.ts 1.2 KB runs code
- assets/app/src/lib/document-types.ts 176 B runs code
- assets/app/src/lib/viewer-config.ts 2.5 KB runs code
- assets/app/src/test/setup.ts 158 B runs code
- assets/app/tests/e2e/markdown-viewer.spec.ts 4.3 KB runs code
- assets/app/tsconfig.json 703 B
- assets/app/vitest.config.ts 430 B runs code
- references/manifest.md 958 B
- scripts/markdown-viewer.sh 1.7 KB runs code
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 · 35 lines · 43 tokens per session scan A 506fd7f0250c
markdown-viewer is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 375 once invoked, about $0.0002 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.