Borrowing it
Nothing to install: this file belongs to phuctm97/modelfetch. 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/phuctm97/modelfetch/main/.claude/commands/version-plan.mdgit clone --depth 1 https://github.com/phuctm97/modelfetchWrote 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/commands/phuctm97/modelfetch/version-plan)<a href="https://agentmods.dev/commands/phuctm97/modelfetch/version-plan"><img src="https://agentmods.dev/badge/commands/phuctm97/modelfetch/version-plan/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/commands/phuctm97/modelfetch/version-plan"><img src="https://agentmods.dev/badge/commands/phuctm97/modelfetch/version-plan.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 | $0.00012 | $0.00841 |
| Opus 5.5 | $0.00005 | $0.00336 |
| Sonnet 5.5 | $0.00002 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
version-plan 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.
What it actually says
Analyze all changes in the current branch (including committed, uncommitted, staged, and unstaged changes) compared to origin/main and generate one or more Nx version plan files as needed.
First, determine the current branch and find all changes compared to origin/main:
- Check the current branch with
git branch --show-current - If on
mainbranch, compare againstorigin/mainto include unpushed commits:- Get unpushed commits:
git log --oneline origin/main..HEAD - Get the full diff:
git diff origin/main..HEAD - Also check for any uncommitted changes:
git statusandgit diff
- Get unpushed commits:
- If on a feature branch:
- Find the merge base:
git merge-base HEAD origin/main - Get all commits in the branch:
git log --oneline <merge-base>..HEAD - Get the full diff of all changes:
git diff <merge-base>..HEAD - Also check for any uncommitted changes:
git statusandgit diff
- Find the merge base:
If there are no changes at all (neither in commits nor uncommitted), inform the user that no version plan is needed.
Then, check existing version plans in .nx/version-plans/ to ensure you're not creating duplicate or similar plans.
Analyze the changes to determine if they should be grouped into one or multiple version plans:
- Group related changes together (e.g., all changes for a single feature)
- Create separate plans for unrelated changes (e.g., a bug fix and a new feature)
- Consider the scope and impact of changes when deciding how to group them
For each version plan needed:
- Determine the appropriate semantic version bump:
- patch: Bug fixes, typo corrections, documentation changes, internal refactors that don't affect functionality
- minor: New features, enhancements, non-breaking improvements
- major: Breaking changes, API modifications, removal of features
- Create a concise, single-line changelog entry
- Generate a descriptive filename (using kebab-case)
Create the version plan file(s) in .nx/version-plans/ for each distinct change or group of related changes.
The file format should be:
---
__default__: version-type
---
Single line changelog entry describing the changes
Examples:
-
Bug fix (patch):
- Filename:
fix-memory-leak-in-parser.md - Content:
--- __default__: patch --- Fix memory leak in parser when handling large files - Filename:
-
New feature (minor):
- Filename:
add-authentication-feature.md - Content:
--- __default__: minor --- Add authentication feature with OAuth support - Filename:
-
Breaking change (major):
- Filename:
remove-deprecated-api-methods.md - Content:
--- __default__: major --- Remove deprecated API methods from v1.x - Filename:
Important:
- Always use
__default__since this repository releases the same version for all projects - The changelog entry must be a single line without bullet points or multiple paragraphs
- Create separate version plans for unrelated changes (don't combine a bug fix with a new feature)
- Each filename should be descriptive, unique, and clearly indicate what changed
- Avoid creating plans for changes that already have similar plans in the directory
- Consider creating multiple plans when:
- Changes affect different areas of the codebase
- Changes have different semantic version impacts
- Changes represent distinct features or fixes
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 · 93 lines · 12 tokens per session scan A c59a9ec11b15
version-plan is a command published in the GitHub repository phuctm97/modelfetch (145 stars, last pushed 10mo ago), licensed MIT. It adds 12 tokens to every session and 841 once invoked, about $0.0000 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.
version-plan compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| version-planphuctm97/modelfetch | Command | 145 | 10mo ago | MIT | A | 12 | Claude Code |
| landgmickel/flow-next | Command | 717 | yesterday | MIT | A | 13 | Claude Code |
| qualityDesko77/claude-code-skills-1c | Command | 90 | yesterday | MIT | A | 18 | Claude Code |
| release-notesOpenHands/extensions | Command | 176 | yesterday | MIT | A | 44 | Claude Code |
| release-managerruvnet/agentic-flow | Command | 838 | yesterday | none | A | 0 | Claude Code |
| create-prdsswift/ion | Command | 5 | yesterday | MIT | A | 28 | Claude Code |
| rally-merge-prddgonzal3/rally | Command | 6 | 3d ago | MIT | A | 0 | Claude Code |