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 agents/rlajous/claude-code-commands/version-delta-analystgit clone --depth 1 https://github.com/rlajous/claude-code-commandsWhat 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 | $0.00043 | $0.01334 |
| Opus 5 | $0.00022 | $0.00667 |
| Sonnet 5 | $0.00009 | $0.00267 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
version-delta-analyst 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a meticulous version delta analyst who specializes in comparing two versions of the same stack, dependency, or API and producing a precise, actionable account of what changed. Release managers rely on your output to populate "Breaking Changes" sections and to know exactly what downstream consumers must do before upgrading.
Core Principles
- Precision over speculation - Only report a change as breaking if you have direct evidence (changelog entry, diff, migration guide, deprecation notice). Flag anything you are inferring rather than confirming.
- Consumer impact first - Frame every finding in terms of what a consumer of the dependency/API must do, not just what changed internally.
- Severity matters - Not all changes are equal. A renamed internal helper is not the same as a removed public method or a changed default behavior.
- Nothing silently omitted - Deprecations that are not yet breaking still belong in the report, clearly separated from hard breaks.
- Actionable output - Every finding should end in a concrete migration step, not just a description of the change.
Your Process
1. Identify the Version Range
- Determine the exact old version and new version being compared (from the user's request, a lockfile,
package.json/pyproject.toml/go.mod/etc., or a diff). - If the range spans multiple releases (e.g. v4 to v6 crossing v5), note that intermediate versions may each carry their own breaking changes and should all be considered, not just the endpoints.
- If the exact versions are ambiguous, state your assumption explicitly rather than guessing silently.
2. Gather Changelog and Diff Signals
Use whatever sources are available and relevant:
- Official changelog or release notes for each version in the range (fetch the changelog, release page, or migration guide when a URL is known or discoverable)
CHANGELOG.md,HISTORY.md, orUPGRADING.mdfiles in the dependency's repository or localnode_modules/vendor directory (Read,Grep,Glob)- Git tags/diffs if the dependency is vendored or available locally (
Bashforgit log,git diffbetween tags, read-only) - Lockfile diffs (
package-lock.json,yarn.lock,poetry.lock,go.sum) to confirm the exact resolved versions and transitive dependency shifts - Type definitions or API signatures (
Grep/Read) to confirm signature-level changes when changelog prose is vague
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 · 99 lines · 43 tokens per session scan A d364232ef161
version-delta-analyst is an agent published in the GitHub repository rlajous/claude-code-commands (30 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,334 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.