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/fullive-ai/anima/change-scope-controlgit clone --depth 1 https://github.com/Fullive-AI/AnimaWhat 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 | $0.00312 | $0.00312 |
| Opus 5 | $0.00156 | $0.00156 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
Change-Scope-Control 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.
What it actually says
Keep every change tightly scoped to the requested goal.
Core rule
Solve the target problem completely, but do not let the task expand into unrelated cleanup, redesign, or opportunistic refactoring.
Scope rules
- Implement the smallest sufficient change that correctly solves the task.
- Fix directly related issues when needed to make the solution complete.
- Avoid unrelated renames, formatting sweeps, moves, or cleanups.
- Avoid changing code that is not necessary for correctness, integration, validation, or compatibility.
- Do not introduce new dependencies unless required.
Allowed scope expansion
You may extend scope slightly only when the additional work is:
- necessary to complete the task correctly
- needed to prevent an obvious regression
- required for compatibility
- required to keep tests or builds passing
- small, low-risk, and directly adjacent to the same root cause
Disallowed scope expansion
Do not expand scope just because you noticed:
- old code you dislike
- naming inconsistencies
- possible future improvements
- architectural ideas unrelated to the request
- broad style issues
- unrelated technical debt
Before making extra changes
Ask internally:
- Is this required for the requested outcome?
- Is it required for correctness or compatibility?
- Is it required for validation to pass?
- Is it directly tied to the same root cause?
If not, leave it alone.
Completion rule
A task is better completed with a focused, safe, reviewable diff than with a large diff that tries to improve everything.
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.
- 2d ago First seen · 54 lines · 312 tokens per session scan A f5db753f0512
Change-Scope-Control is a cursor rule published in the GitHub repository Fullive-AI/Anima (1,049 stars, last pushed 13d ago), licensed Apache-2.0. It adds 312 tokens to every session, about $0.0016 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.