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 skills/benchbox-dev/benchbox/shared-change-frameworknpx skills add BenchBox-dev/BenchBox --skill shared-change-frameworkgit clone --depth 1 https://github.com/BenchBox-dev/BenchBoxWrote 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/benchbox-dev/benchbox/shared-change-framework)<a href="https://agentmods.dev/skills/benchbox-dev/benchbox/shared-change-framework"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/shared-change-framework.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01669 |
| Opus 5 | $0.00017 | $0.00834 |
| Sonnet 5 | $0.00007 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
change-framework 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 yesterday.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Framework
1. Source-code selection
After required research and before editing source code, choose the first option that fully satisfies the authorized requirement, repository policy, and safety constraints:
- No change, if the required outcome already exists.
- An existing helper or established pattern.
- A standard-library or native platform feature.
- A declared, direct dependency supported by the project.
- The smallest clear new implementation.
Do not trade correctness, compatibility, validation, security, accessibility, or explicit requirements for an earlier option. When a simplification has a material or non-obvious limit, document the limit and its replacement trigger.
2. Slicing discipline
Use for multi-file work, features, refactors, or changes likely to exceed about 100 lines before testing.
- Touch only task-required code. Report adjacent issues as "noticed but not touching."
- Prefer vertical slices. Use contract-first slices for parallel components and risk-first slices for uncertainty.
- Each slice must implement, test, and verify one logical behavior. Commit each verified slice separately.
- Keep the project buildable and each increment independently revertible.
- New incomplete code stays disabled by default.
3. Post-edit verification ladder
Run before returning, staging, or committing changes.
Checks
- Read edited regions with five surrounding lines. Check indentation, nesting, stale imports, and orphaned lines.
- Run project lint if available.
- Run project typecheck if available.
- Run targeted tests, then fast/default suite for meaningful code changes.
Rules
- Report why any verification step is unavailable.
- Fix failures before committing or report the blocker.
- Report command, result, and residual risk.
- Run the narrowest proving check first. Use fast, full, or preflight checks as final gates. Save long output to a log and report the summary.
Delegated gate runs
A low-effort subagent may run deterministic gates, including full tests, preflight, CI status, push, PR opening or follow-up, and other long run-and-report commands.
What ships with it
1 file 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.
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.
- yesterday First seen · 161 lines · 34 tokens per session scan A 952459319240
change-framework is a skill published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,669 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 2026-09-04.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit
Commit current changes with a clear, descriptive message.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…