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 rules/haroon966/pinky-cursor/09-context-disciplinegit clone --depth 1 https://github.com/Haroon966/pinky-cursorWrote 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/rules/haroon966/pinky-cursor/09-context-discipline)<a href="https://agentmods.dev/rules/haroon966/pinky-cursor/09-context-discipline"><img src="https://agentmods.dev/badge/rules/haroon966/pinky-cursor/09-context-discipline.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 | $0.00249 | $0.00249 |
| Opus 5 | $0.00125 | $0.00125 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
09-context-discipline 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 5d 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
Context discipline (ALWAYS ON)
Pinky rules stay always on until the user opts out. Skills are available by default — but do not load everything into context.
Do
- Read / open only files needed for this user prompt.
- For skills: load one matching
SKILL.md(and its companions only if that skill says so). Never bulk-read all ofskills/. - Prefer search/grep over opening whole trees.
- Keep replies Caveman-short so tokens stay low.
Don't
- Don't preload every Pinky skill, format doc, or rule file "just in case".
- Don't dump
ADR-FORMAT.md/CONTEXT-FORMAT.mdunless running/grill-with-docs. - Don't attach the whole kit README/INSTALL into every turn after install.
Opt out
User says "stop caveman", "normal mode", "don't use pinky", "disable [skill/rule]" → stop that layer for the session (or until they re-enable).
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.
- 5d ago First seen · 26 lines · 249 tokens per session scan A 8e43cb336c60
09-context-discipline is a cursor rule published in the GitHub repository Haroon966/pinky-cursor (4 stars, last pushed 26d ago), licensed MIT. It adds 249 tokens to every session, about $0.0012 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.