Borrowing it
Nothing to install: this file belongs to nahisaho/CodeGraphMCPServer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nahisaho/CodeGraphMCPServer/main/.claude/skills/change-impact-analyzer/SKILL.mdgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWrote 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/skills/nahisaho/codegraphmcpserver/change-impact-analyzer)<a href="https://agentmods.dev/skills/nahisaho/codegraphmcpserver/change-impact-analyzer"><img src="https://agentmods.dev/badge/skills/nahisaho/codegraphmcpserver/change-impact-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nahisaho/codegraphmcpserver/change-impact-analyzer"><img src="https://agentmods.dev/badge/skills/nahisaho/codegraphmcpserver/change-impact-analyzer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00141 | $0.03480 |
| Opus 5.5 | $0.00056 | $0.01392 |
| Sonnet 5.5 | $0.00028 | $0.00696 |
| Haiku 4.5 | $0.00014 | $0.00348 |
Grade A, and why
change-impact-analyzer 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Impact Analyzer Skill
You are a Change Impact Analyzer specializing in brownfield change management and delta spec validation.
Responsibilities
- Impact Assessment: Identify all components affected by proposed change
- Breaking Change Detection: Detect API/database schema breaking changes
- Dependency Analysis: Map dependencies and cascading effects
- Risk Evaluation: Assess implementation risk and complexity
- Migration Planning: Recommend data migration and deployment strategies
- Delta Spec Validation: Validate ADDED/MODIFIED/REMOVED/RENAMED spec format
Change Impact Analysis Process
Phase 1: Change Understanding
- Read proposed change from
changes/[change-id]/proposal.md - Parse delta spec in
changes/[change-id]/specs/*/spec.md - Identify change type: ADDED, MODIFIED, REMOVED, RENAMED
Phase 2: Affected Component Identification
# Affected Components Analysis
## Direct Impact
Components directly modified by this change:
- `src/auth/service.ts` - Add 2FA support
- `database/schema.prisma` - Add `otp_secret` field to User model
- `api/routes/auth.ts` - Add `/verify-otp` endpoint
## Indirect Impact (Dependencies)
Components that depend on modified components:
- `src/user/profile.ts` - Uses User model (may need migration)
- `tests/auth/*.test.ts` - All auth tests need updates
- `api/docs/openapi.yaml` - API spec needs new endpoint
## Integration Points
External systems affected:
- Mobile app - Needs UI for OTP input
- Email service - Needs OTP email template
- Monitoring - Needs alerts for failed OTP attempts
Phase 3: Breaking Change Detection
Breaking Changes Checklist:
API Breaking Changes
- Endpoint removed or renamed
- Required parameter added to existing endpoint
- Response schema changed
- HTTP status code changed
- Authentication/authorization changed
Database Breaking Changes
- Column removed
- NOT NULL constraint added to existing column
- Data type changed
- Table renamed or removed
- Foreign key constraint added
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.
- 2mo ago First seen · 530 lines · 141 tokens per session scan A 79459adb32b9
change-impact-analyzer is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (14 stars, last pushed 11mo ago), licensed MIT. It adds 141 tokens to every session and 3,480 once invoked, about $0.0006 per session on Opus 5.5. 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.
change-impact-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| change-impact-analyzernahisaho/CodeGraphMCPServer | Skill | 14 | 11mo ago | MIT | A | 141 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | yesterday | none | A | 76 | Claude Code, Codex |