What is codeimpact CLAUDE.md?

A project guide for CodeImpact, a code-analysis tool that maps unused code, test effects, dependencies, and change impact.

Use it to find dead code, identify tests for changed files, estimate a change’s blast radius, and run pre-commit verification.

It defines which CodeImpact checks to run before searching, editing, or finalizing code, helping reveal affected areas and possible conflicts.

codeimpact CLAUDE.md — Instructions file by abhisavakar

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 instructions/abhisavakar/codeimpact/claude-md

Clone the repo

git clone --depth 1 https://github.com/abhisavakar/codeimpact

Per session 2,782 This file is loaded in full into every session.

When invoked 2,782 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	$0.02782	$0.02782
Opus 5	$0.01391	$0.01391
Sonnet 5	$0.00556	$0.00556
Haiku 4.5	$0.00278	$0.00278

Measured 2d ago against content hash 5058b6cc5f44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codeimpact CLAUDE.md 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.

CLAUDE.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions

CLI Commands

codeimpact deadcode              # Find unused exports and dead code
codeimpact test-impact --changed src/file.ts  # Tests to run for changed files
codeimpact impact src/core/engine.ts          # Blast radius analysis
codeimpact stats                 # Token usage statistics
codeimpact reindex               # Force reindex after git issues

CodeImpact Integration

CodeImpact provides intelligent code analysis. Use these tools FIRST before falling back to built-in tools.

Tool Preferences (IMPORTANT)

For code searches and questions about the codebase:
- Use mcp__codeimpact__memory_query FIRST (759x faster than grep, returns context)
- Only fall back to Grep/Glob if CodeImpact returns no results
Before writing or suggesting code changes:
- Run mcp__codeimpact__memory_review to check against patterns, past decisions, and potential conflicts
- This catches hallucinated imports, duplicate functions, and pattern violations
Before finalizing/committing code:
- Run mcp__codeimpact__memory_verify for pre-commit quality checks
- Catches security issues, missing dependencies, and import errors
At session start:
- Run mcp__codeimpact__memory_status to get project overview and recent changes
For impact analysis:
- Use mcp__codeimpact__memory_blast_radius to analyze risk of changing a file
- Shows affected files, critical paths, and recommendations

Why Use CodeImpact Tools?

Semantic search: Understands intent, not just keywords
Pattern awareness: Knows project conventions and enforces them
Decision memory: Remembers past architectural decisions
Déjà vu detection: Surfaces similar past problems you've solved
Import validation: Catches hallucinated imports before they break builds
Blast radius: Understand impact and risk before making changes

Quick Reference

Task	Tool	Example
Find code	`memory_query`	"how does auth work?"
Check code	`memory_review`	Before suggesting changes
Verify code	`memory_verify`	Before committing
Project status	`memory_status`	At session start
Save decision	`memory_record`	After architectural choices
Impact analysis	`memory_blast_radius`	Before modifying critical files

Read the full file on GitHub · 234 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.

2d ago First seen · 234 lines · 2,782 tokens per session scan A 5058b6cc5f44

Subscribe to this mod's changes

codeimpact CLAUDE.md is an instructions file published in the GitHub repository abhisavakar/codeimpact (3 stars, last pushed 3mo ago), licensed MIT. It adds 2,782 tokens to every session, about $0.0139 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.

Git and workflow Testing

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codeimpact CLAUDE.md