10-documentation

A set of documentation rules based on separate contracts, where each document has one clear responsibility. It defines an index, project context, and working-mode information for keeping project documentation useful to people and coding agents.

In plain words
What is it for?
Use it when organizing project documentation, recording the project purpose and current working mode, and maintaining documentation as part of implementation.
Why use it?
It prevents documentation from becoming a scattered collection of outdated generic files and makes the authoritative information easier to locate.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/conlinjoe/ai-platform/10-documentation
Clone the repo
git clone --depth 1 https://github.com/ConlinJoe/ai-platform

Made for: Cursor.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,102 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.02102
Opus 5 $0.00005 $0.01051
Sonnet 5 $0.00002 $0.00420
Haiku 4.5 $0.00001 $0.00210

Measured 2d ago against content hash 1e1db074e03b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

10-documentation 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 2d 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.

.cursor/rules/10-documentation.mdc · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation

Documentation is a collection of contracts, not a fixed set of generic markdown files. Each contract has a single responsibility. Documentation is part of the implementation.

Contract Model

Index

docs/README.md is the documentation index, dependency graph, and contract registry.

Every project defines its own contract layout. The platform does not mandate specific filenames beyond the index, project context file, working-mode file, and metadata requirements.

Project Context

docs/00-project-context.md is the concise entry point for ChatGPT Projects and high-level agent context. Keep it current when purpose, stack, or constraints change.

Working Mode

docs/working-mode.md is operational continuation state for a fresh agent: current working mode, what to preserve, minimum orientation, in-mode scope, and mode-specific prohibitions.

Keep it small. Point at authoritative docs; do not copy architecture, vision, status, or standing constraints into it. Do not recopy platform-wide safety rules.

Update it only when the working mode itself changes — for example architecture → implementation, implementation → stabilization, site-wide design → individual polish, audit → remediation, pre-launch → launch, or a major decision that changes how future agents should operate. Do not rewrite it after routine bounded tasks.

It is not a second project-context document and not a progress log. Progress, validation, and readiness stay in docs/99-project-status.md.

Contract Types

Type Purpose
foundational Vision, domain model, platform-wide architecture
engine Subsystem or bounded context
feature User-visible or API feature behavior
adr Single architecture decision (one decision per file)
planning Roadmaps, spikes, temporary plans (not implementation authority)
status Current implementation status, phase progress, validation, readiness (not architectural authority)
continuation Current working mode and agent continuation instructions (not architectural authority)

Read the full file on GitHub · 266 lines

Changes

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.

  1. 2d ago First seen · 266 lines · 11 tokens per session scan A 1e1db074e03b

Subscribe to this mod's changes

10-documentation is a cursor rule published in the GitHub repository ConlinJoe/ai-platform (2 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 2,102 once invoked, about $0.0001 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.