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/mghareeb/code-change-impact/code-change-impactgit clone --depth 1 https://github.com/mghareeb/code-change-impactWhat 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 | $0.00122 | $0.00900 |
| Opus 5 | $0.00061 | $0.00450 |
| Sonnet 5 | $0.00024 | $0.00180 |
| Haiku 4.5 | $0.00012 | $0.00090 |
Grade A, and why
code-change-impact 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Change Impact (Cursor rule)
A fix is "done" only when you know what it touched besides the target. Find the ripples, then prove nothing else broke. Run against the VCS diff.
Procedure
0. Discover. Establish the repo root + diff; languages (from manifests); the project's own typecheck/build/test/lint commands (read scripts/Makefile/CI, don't guess); and the import style + path aliases. A repo may mix stacks.
1. Epicenter. git diff HEAD (or git diff <base>...HEAD); read the hunks.
Classify each changed file: shared/core · public/exported symbol · type/interface/
schema · serialized contract (REST/GraphQL/DTO/proto) · config/registry · DB
schema/migration · global config/styles · build/deps · generated/duplicated twin ·
or a local leaf.
2. Reverse dependencies. For each changed symbol, grep who imports the module and who calls the symbol (this language's import form). Build directly-impacted + transitively-impacted, then map to runnable surfaces (route/endpoint/command/job).
3. Behavioral impact. Per site: shape/signature/default/side-effect/invariant change, or internal/safe? Split build-caught ripples (typed langs) from silent ripples — cache/memo keys, changed default/sort, serialization/enum drift, global/persisted state, concurrency & transactions, locale/format, regex/ validation, flag defaults, theme/i18n. Check mirror/twin files: regenerate generated code, sync cross-language duplicated constants. One side edited without the other is an impact finding even if it compiles.
4. Verify. Run discovered commands cheapest-first, scaled to reach: typecheck → build → tests (prefer targeted) → lint. Then exercise the impacted surfaces and watch logs/errors. Green local ≠ deployed.
5. Report with the template below.
Report template (always)
# Code Change Impact: <one-line description>
## Verdict: SAFE | SAFE WITH CAVEATS | IMPACT FOUND
## Epicenter
- <file:line> — <coupling class> — <what changed>
## Blast radius
### Directly impacted
- <file / surface> — <route/endpoint/command> — <why> — risk: High|Med|Low
### Transitively impacted — <…> (or none)
## Mirror / twin files — <file to sync, in sync? yes/NO> (or none)
## Silent-risk callouts (build won't catch) — <…> (or none)
## Verification
- typecheck/build/tests: PASS/FAIL
- surfaces exercised: <list> → clean? errors?
## Residual risk & manual checklist
- [ ] <not auto-verifiable>
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 · 73 lines · 122 tokens per session scan A 2132d66cb26c
code-change-impact is a cursor rule published in the GitHub repository mghareeb/code-change-impact (2 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 900 once invoked, about $0.0006 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
nopua
The anti-PUA. Drives AI with wisdom and trust instead of fear. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, stuck in loops, passive behavior.
visualcave
Use when the user asks to create a diagram, chart, infographic, flowchart, architecture illustration, or any technical visualization. Covers flowcharts, sequence diagrams, ER diagrams, class diagrams, state machines, timelines, mind maps, git graphs, pie charts, and quadrant charts.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
fix-issue
Implement a fix following the human-thinking loop — understand the root cause, plan the minimal change, implement, verify the problem is actually gone.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
swift
Swift patterns: SwiftUI, actors, async/await, value types.