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 shawnpang/startup-founder-skills --skill support-docsgit clone --depth 1 https://github.com/shawnpang/startup-founder-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/shawnpang/startup-founder-skills/support-docs)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/support-docs"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/support-docs/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/shawnpang/startup-founder-skills/support-docs"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/support-docs.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 | $0.00030 | $0.01859 |
| Opus 5 | $0.00015 | $0.00929 |
| Sonnet 5 | $0.00006 | $0.00372 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade A, and why
support-docs scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Structure: endpoint + method, authentication, request parameters (table with name/type/required/description), example request (working curl), response examples (success + every error code), and rate limits. Every code sn Copies of this mod
1 near-identical copy found in the catalogue:
- support-docs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Documentation
When to Use
Activate when a founder or team member needs to create customer-facing documentation that helps users solve problems independently. This includes prompts like "write a help center article," "create an FAQ," "document our API," "write a troubleshooting guide," "build a getting-started guide," or "our support tickets keep asking the same questions."
Context Required
- From startup-context: product type, target user technical level, existing documentation (if any), top support ticket categories, and tools used for docs hosting (e.g., Notion, GitBook, Zendesk, ReadMe).
- From the user: the specific topic to document, the target audience (end users, admins, developers), the user's technical sophistication, common failure modes or confusion points, and whether this is a new article or an update to existing content.
Workflow
- Identify document type — Determine which template fits: help center article, FAQ, troubleshooting guide, API reference, or getting-started guide. Each serves a different user intent.
- Define the user's entry point — How will someone find this document? Search query, error message, support agent link, in-app help button? This determines the title and opening line.
- Write in problem-solution format — Lead with the user's problem (in their words), then provide the solution. Never start with product architecture explanations.
- Apply progressive disclosure — Put the most common answer first. Nest edge cases, advanced options, and technical details in expandable sections or later in the article.
- Add searchability elements — Include the exact error messages, feature names, and colloquial terms users search for. Repeat key terms naturally.
- Test with the "3 AM rule" — Read the article as if you are a frustrated user at 3 AM with a broken workflow. Does it get you to a solution in under 2 minutes? If not, restructure.
- Link related articles — Add "Related" or "Next steps" links at the bottom to keep users in the self-serve flow.
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.
- 10d ago First seen · 144 lines · 30 tokens per session scan A a30eddc0f2e0
support-docs is a skill published in the GitHub repository shawnpang/startup-founder-skills (320 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 1,859 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.