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 signnow/sn-mcp-server --skill sn-spec-writinggit clone --depth 1 https://github.com/signnow/sn-mcp-serverWrote 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/signnow/sn-mcp-server/sn-spec-writing)<a href="https://agentmods.dev/skills/signnow/sn-mcp-server/sn-spec-writing"><img src="https://agentmods.dev/badge/skills/signnow/sn-mcp-server/sn-spec-writing/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/signnow/sn-mcp-server/sn-spec-writing"><img src="https://agentmods.dev/badge/skills/signnow/sn-mcp-server/sn-spec-writing.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 | $0.00087 | $0.01037 |
| Opus 5 | $0.00044 | $0.00518 |
| Sonnet 5 | $0.00017 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
sn-spec-writing 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 11d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Specification Writing
Analysis Protocol
Before designing any feature, run every check in order. If any check fails, reject or redesign before proceeding.
1. Philosophy Check
| Principle | Question |
|---|---|
| Thin Translator | Does this maintain the stateless translation identity? If it adds state, caching, or agent-side logic — redesign. |
| Simplicity | Is this the simplest possible solution? Can it have fewer moving parts? |
| YAGNI | Is the feature actually needed now, or is it speculative? |
2. Architecture & Layer Check
- Which layers are affected? Consult the layer access matrix (skill:
sn-architecture). - Upward imports (
signnow_client/→sn_mcp_server/)? → Reject. - Tool functions importing Starlette or referencing HTTP headers? → Redesign to use
TokenProvider. - Module-level mutable state, global caches, singletons? → Reject.
3. Tool Design Check
- Does this need a new MCP tool? Can the functionality join an existing tool instead?
- If new: does it overlap with existing tools? Could one tool handle both with an internal branch?
- Are parameters minimal and clear? Can an agent use this from the docstring alone?
- Does the response model include only decision-relevant fields? No raw API passthrough.
4. Auth & Transport Check
- Works across all 3 auth strategies (password grant, bearer header, OAuth2 JWT)?
- Works across all 3 transports (STDIO, Streamable HTTP, SSE)?
- No deployment-environment assumptions?
5. Error Handling Check
- List every failure mode explicitly.
- Each failure mode: specific error message with operation name, entity ID, cause.
- SignNow API errors translated via
signnow_client/exceptions.py. - Pydantic validation errors surfaced as clear parameter-level messages before any API call.
6. Testability Check
- Business logic testable by injecting a mocked
SignNowAPIClient? - List test cases: happy path + each failure mode.
- Any tests require network calls? → Redesign.
- New tests mirror
tests/unit/source structure.
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.
- 11d ago First seen · 105 lines · 87 tokens per session scan A d4b717898ef4
sn-spec-writing is a skill published in the GitHub repository signnow/sn-mcp-server (8 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,037 once invoked, about $0.0004 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
webhook-handler-patterns
Best practices for webhook handlers: verify → parse → handle idempotently. Covers idempotency, error handling, retry logic, framework-specific gotchas (Express, Next.js, FastAPI). Use when implementing any webhook receiver.
api
FastAPI + async/sync HTTP client patterns, JWT auth, multi-provider routing, Pydantic request/response models, CORS, background tasks, and typed frontend API clients — synthesized from lead-gen-engine and seo-geo-aeo-engine.
webfetch
Fetch live web pages, inspect responses, extract relevant content, and summarize findings with links.
free-business-template-library
Finds relevant PandaDoc business document templates in a catalog of 1,000+ free templates and returns direct links for customization and eSignature. Use when the user asks for a ready-made business document template or wants to find, browse, compare, or select PandaDoc templates for proposals, contracts, agreements…
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…