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 instructions/raydestar/sir-thaddeus/documentation-standardsgit clone --depth 1 https://github.com/raydeStar/sir-thaddeusWrote 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/instructions/raydestar/sir-thaddeus/documentation-standards)<a href="https://agentmods.dev/instructions/raydestar/sir-thaddeus/documentation-standards"><img src="https://agentmods.dev/badge/instructions/raydestar/sir-thaddeus/documentation-standards.svg" alt="Measured on agentmods" 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 | $0.00421 | $0.00421 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
Documentation Writing Standards 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 4d 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
Documentation Writing Standards
These rules apply to every agent editing user-facing documentation in this repository — not just the readme-specialist. They ensure a consistent voice, accurate claims, and a trustworthy first impression.
Voice and Tone
- Write clearly and simply. Prefer short paragraphs.
- Use a calm, confident tone — not breathless, not timid.
- Favor concrete language over abstractions.
- Avoid hype-heavy startup language and pitch-deck phrasing.
Accuracy
- Match the repo's actual capabilities. Do not claim unverified features.
- Preserve accurate links, commands, filenames, and doc references.
- If a claim cannot be verified from the codebase, soften the wording or flag it.
Platform Claims
- Verified support → "runs on."
- Intended but untested → "designed for" or "built for."
- Single-platform today → state that plainly.
Structure
- Keep the top of any README sparse and scannable.
- Explain what the product is in plain language before architecture.
- Put advanced technical material below the fold (use
<details>where appropriate). - Quick Start sections: 5 steps max, practical, no preamble.
Privacy and Trust Language
Sir Thaddeus is a local-first AI copilot. Its positioning centers on user control, explicit permissions, visible actions, and privacy. When editing docs:
- Make privacy and control easy to understand.
- Do not overstate security or privacy guarantees.
- Prefer honest, specific language over impressive-sounding generalities.
Priority Order
When multiple improvements compete, choose in this order:
- Accuracy
- Clarity
- First-time user comprehension
- Trustworthiness
- Brevity
- Elegance
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.
- 4d ago First seen · 58 lines · 421 tokens per session scan A fab2540a249d
Documentation Writing Standards is an instructions file published in the GitHub repository raydeStar/sir-thaddeus (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 421 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
llm-swarm-router AGENTS.md
AGENTS.md instructions for matthewdcage/llm-swarm-router, covering agent & developer guide, dox rail, project overview, architecture and repository layout.
llm-swarm-router CLAUDE.md
Claude Code instructions for matthewdcage/llm-swarm-router, covering claude code: swarm-llm and honcho memory (mcp).
mcp-local-llm AGENTS.md
Instructions for aplaceforallmystuff/mcp-local-llm, covering agents.md - mcp-local-llm, tech stack, architecture, development commands and environment variables.
WPFVisualTreeMcp CLAUDE.md
Instructions for faze79/WPFVisualTreeMcp, covering claude.md, project overview, build commands, build solution and build for release.
Tool_MCP_LMStudio AGENTS.md
AGENTS.md instructions for Ka1y0/Tool_MCP_LMStudio, covering agents.md, mission, architecture, safety invariants and commands.
anjian-agent CLAUDE.md
Claude Code instructions for ck3938700-ship-it/anjian-agent, covering claude code 维护上下文：安鉴台, 产品目标, 不可破坏的安全原则, 技术结构 and 每次修改的完成标准.