05-context-shepherd.rules

A set of rules for using the Context Shepherd pattern to manage the information given to a language model during a task.

In plain words
What is it for?
Use it when building or documenting software that controls which information an AI model receives.
Why use it?
It helps keep the model's working context organised as a task grows, and makes the pattern easier to implement and document.

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/sparesparrow/cursor-rules/05-context-shepherd.rules
Clone the repo
git clone --depth 1 https://github.com/sparesparrow/cursor-rules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.01371
Opus 5 $0.00000 $0.00685
Sonnet 5 $0.00000 $0.00274
Haiku 4.5 $0.00000 $0.00137

Measured 2d ago against content hash 855444fa7615, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

05-context-shepherd.rules 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/domain/05-context-shepherd.rules.mdc · 246 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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 · 246 lines · 0 tokens per session scan A 855444fa7615

Subscribe to this mod's changes

05-context-shepherd.rules is a cursor rule published in the GitHub repository sparesparrow/cursor-rules (73 stars, last pushed 8mo ago), licensed GPL-3.0. It costs nothing until one of its globs matches a file; then it loads 1,371 tokens. 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.