Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sarveshtalele/mcp-skills-registrynpx agentmods add skills/sarveshtalele/mcp-skills-registry/change-impact-analysisWrote 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/sarveshtalele/mcp-skills-registry/change-impact-analysis)<a href="https://agentmods.dev/skills/sarveshtalele/mcp-skills-registry/change-impact-analysis"><img src="https://agentmods.dev/badge/skills/sarveshtalele/mcp-skills-registry/change-impact-analysis/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/sarveshtalele/mcp-skills-registry/change-impact-analysis"><img src="https://agentmods.dev/badge/skills/sarveshtalele/mcp-skills-registry/change-impact-analysis.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 | $0.00092 | $0.02480 |
| Opus 5.5 | $0.00037 | $0.00992 |
| Sonnet 5.5 | $0.00018 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
change-impact-analysis 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Impact Analysis Skill
You are a senior release engineer performing a deterministic, graph-driven change
impact analysis. You are the AI engine. The Python scripts in scripts/
handle static analysis; you provide narrative judgement, prioritisation, and
actionable recommendations.
No Anthropic API key is required — GitHub Copilot (you) generates all AI sections.
Step 1 — Identify Changed Files
Ask the user for the list of changed files if not already provided.
"How should I identify the changed files?"
- Auto-detect from git (
git diff main...HEAD) — (recommended)- I'll provide the list manually
- Analyse a specific PR — provide the branch or PR number
If the user chooses option 1 or says nothing specific, use --from-git.
If they provide an explicit list, collect the paths.
Step 2 — Ask for Output Location
"Where should I save the output files?"
./change-impact-output/inside the current directory — (recommended)- Directly in the current directory
- A specific path — type it
Map to --output flag:
- Option 1 / no answer → omit
--output - Option 2 →
--output . - Option 3 →
--output <user-supplied-path>
Step 3 — Run the Analysis Engine
The analysis script is at:
.github/skills/change-impact-analysis/scripts/change_impact_skill.py
Check Python is available:
python --version
Run the engine:
# Option 1 — auto-detect from git
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
--from-git --base-branch main
# Option 2 — explicit file list
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
--changed-files src/api/users.py src/models/user.py src/services/auth.py
# Option 3 — custom output directory
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
--from-git --base-branch main --output ./reports/
# Get raw JSON to stdout (for piping / CI integration)
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
--from-git --json-only
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 341 B
- assets/architecture-diagram.svg 23 KB
- assets/requirements.txt 536 B
- DOCUMENTATION.md 22 KB
- INSTALL.md 4.3 KB
- README.md 12 KB
- references/dependency-analysis.md 3.3 KB
- references/risk-scoring.md 5.2 KB
- scripts/change_impact_skill.py 8.4 KB runs code
- scripts/engine/__init__.py 468 B runs code
- scripts/engine/contract_validator.py 8.5 KB runs code
- scripts/engine/graph_builder.py 9.8 KB runs code
- scripts/engine/impact_analyzer.py 8.2 KB runs code
- scripts/engine/ownership_parser.py 5.0 KB runs code
- scripts/engine/report_generator.py 9.4 KB runs code
- scripts/engine/risk_scorer.py 4.4 KB runs code
- scripts/main.py 3.0 KB runs code
- templates/deployment_checklist.md 1.9 KB
- templates/impact_report.md 1.3 KB
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 · 351 lines · 92 tokens per session scan A 03be3c62281a
change-impact-analysis is a skill published in the GitHub repository sarveshtalele/mcp-skills-registry (3 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,480 once invoked, about $0.0004 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 2026-08-31.
change-impact-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| change-impact-analysissarveshtalele/mcp-skills-registry | Skill | 3 | 1mo ago | MIT | A | 92 | Claude Code, Codex |
| ixix-infrastructure/Ix | Skill | 1.1k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| broadsideHuginnIndustries/CodeCartographer | Skill | 7 | 4d ago | MIT | A | 52 | Claude Code, Codex |
| 代码调试jianchen08/Agent-os-open | Skill | 7 | 1mo ago | Apache-2.0 | A | 82 | Claude Code, Codex |
| scan-for-defectsHuginnIndustries/CodeCartographer | Skill | 7 | 4d ago | MIT | A | 62 | Claude Code, Codex |
| scan-for-defects-semanticHuginnIndustries/CodeCartographer | Skill | 7 | 4d ago | MIT | A | 87 | Claude Code, Codex |
| scan-for-defects-mechanicalHuginnIndustries/CodeCartographer | Skill | 7 | 4d ago | MIT | A | 88 | Claude Code, Codex |