A mandatory Cursor rule that makes .ai-context the project's main source of workflow and continuity instructions. It defines which overview, standards, planning, structure, and session files to read at different stages of work.

Use it to bootstrap a Cursor session, orient work in an unfamiliar codebase, plan non-trivial changes, continue earlier sessions, and follow the project's coding and testing rules.

It gives each session a consistent starting point and helps the agent follow project-specific standards. It also requires plans for larger changes and tests before committing.

main — Cursor rule by dkothule

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/dkothule/ai-context/main

Clone the repo

git clone --depth 1 https://github.com/dkothule/ai-context

Made for: Cursor.

Per session 634 This file is loaded in full into every session.

When invoked 634 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00634	$0.00634
Opus 5	$0.00317	$0.00317
Sonnet 5	$0.00127	$0.00127
Haiku 4.5	$0.00063	$0.00063

Measured yesterday against content hash 9a29466737d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

main 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 yesterday.

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/main.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

description: Bootstrap Cursor to shared .ai-context instructions globs: alwaysApply: true

Cursor Adapter Rule

Use .ai-context/ as the single source of truth for project workflow, standards, and session continuity. This rule is intentionally thin.

Session Start

Always read for orientation:

.ai-context/project.overview.md
.ai-context/project.changelog.md
Latest file in .ai-context/sessions/ (excluding _archive/)

Then read based on task:

Writing/modifying code → standards/project.rules.base.md, project.rules.md
Planning non-trivial work → project.tasks.md, plans/
Understanding codebase layout → project.structure.md
Continuing prior work → additional files in sessions/
Language/testing specifics → files in standards/

Planning

Before non-trivial work (multi-session, architectural change, external dependency), write a plan to .ai-context/plans/YYYY-MM-DD-<topic>.md using _template.md. Reference it from project.tasks.md.

During Work

Follow .ai-context/standards/project.rules.base.md and project.rules.md.
One logical change per commit; tests run before commit.
Route state changes to the right .ai-context/ file: decision → project.decisions.md, user-visible change → project.changelog.md, task transition → project.tasks.md, plan → plans/, session close → sessions/.

Session End (Mandatory)

Write .ai-context/sessions/YYYY-MM-DD-<topic>.md from _template.md. Multiple logs per day are fine — one per topic.
Update project.tasks.md, project.decisions.md, project.changelog.md as applicable.

Hooks

Cursor session hooks are configured in .cursor/hooks.json:

preCompact autosaves the working transcript to .ai-context/sessions/YYYY-MM-DD-HHMM-precompact-autosave.md before compaction. After compaction, review the autosave, curate it into a proper session log, record the autosave filename as source_autosave, copy its local_transcript_ref if present, then delete the autosave. Treat local_transcript_ref as a local/private fallback pointer, not the durable handoff.
sessionEnd reminds you to write a session log if today's log is missing.
sessionStart surfaces any pending autosave for curation.

Read the full file on GitHub · 48 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.

yesterday First seen · 48 lines · 634 tokens per session scan A 9a29466737d7

Subscribe to this mod's changes

main is a cursor rule published in the GitHub repository dkothule/ai-context (11 stars, last pushed 3mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.

Planning Productivity Testing

main

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Cursor Adapter Rule

Session Start

Planning

During Work

Session End (Mandatory)

Hooks

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs