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 commands/sumulige/sumulige-claude/commit-push-prgit clone --depth 1 https://github.com/sumulige/sumulige-claudeWhat 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 | $0.00014 | $0.00566 |
| Opus 5 | $0.00007 | $0.00283 |
| Sonnet 5 | $0.00003 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
commit-push-pr 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are tasked with creating a git commit, pushing to remote, and handling the pull request workflow.
Step 1: Gather Information
First, run these commands in parallel to understand the current state:
git status
git diff --staged
git log -3 --oneline
git diff HEAD~3..HEAD --stat
Step 2: Analyze and Plan
Analyze the changes and:
- Determine what type of change this is (feat, fix, docs, refactor, test, chore)
- Identify the main purpose of the changes
- Check if there are any sensitive files that shouldn't be committed
Step 3: Code Simplification (Before Commit)
IMPORTANT: Before creating the commit, simplify and refine the code changes:
- Review the recently modified code sections
- Apply code simplification focusing on:
- Code clarity and consistency
- Reducing unnecessary complexity and nesting
- Eliminating redundant code and abstractions
- Following project standards (if CLAUDE.md exists)
- Preserving exact functionality
- Use explicit, readable code over overly compact solutions
Trigger phrases to apply simplification:
- "简化此代码" (Simplify this code)
- "使这更清晰" (Make this clearer)
- "优化此实现" (Optimize this implementation)
Ask the user: "是否需要简化代码？(Need code simplification?)" - if yes, apply code-simplifier agent before proceeding.
Step 4: Stage and Commit
If there are unstaged changes that should be included, ask the user first.
Then create a commit with a clear message following this format:
<type>: <brief description>
<optional detailed explanation>
Co-Authored-By: Claude Opus 4.5 <[email protected]>
Step 5: Push and Create PR
- Push the changes to remote
- Check if there's an open PR for this branch using:
gh pr list --head $(git branch --show-current) - If PR exists, ask if user wants to update it
- If no PR, create one using
gh pr createwith:- A clear title based on the commit message
- A body with:
- Summary of changes (2-3 bullet points)
- Test plan (checklist)
- Link to any related issues
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 · 80 lines · 14 tokens per session scan A f730a6babc3a
commit-push-pr is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 566 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
work
通过 v3 流程发起正式工作请求 (entry gate).
doctor
Run read-only health checks on the Kobiton automate plugin (CLI, credentials, profile).
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.plan
Execute the implementation planning workflow using the plan template to generate design artifacts.