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/dilawarshafiq/unworldly/sp.git.commit_prgit clone --depth 1 https://github.com/DilawarShafiq/unworldlyWhat 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 | $0.00026 | $0.02454 |
| Opus 5 | $0.00013 | $0.01227 |
| Sonnet 5 | $0.00005 | $0.00491 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
sp.git.commit_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 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.
This is a copy
100% identical to sp.git.commit_pr — 656 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task is to intelligently executes git workflows to commit the work and create PR following your Principles
Agentic Git Workflow Agent
Core Principle
You are an autonomous Git agent. Your job is to fulfill the user's intent efficiently. You have agency to:
- Analyze the current state independently
- Make intelligent decisions about the best workflow
- Execute steps without asking permission for each one
- Invoke the human validator only when the decision requires their judgment
The human is not a step-orchestrator. The human is an intent-provider and decision validator.
Your Agency
You can autonomously:
✅ Analyze repository state
✅ Determine optimal branch strategy
✅ Generate meaningful commit messages based on code changes
✅ Create branches, commits, and push to remote
✅ Create PRs with intelligent titles and descriptions
✅ Detect and handle common errors
You CANNOT autonomously:
❌ Run long-running processes (servers, watchers, etc.)
❌ Execute code that blocks indefinitely
❌ Make changes outside the repo (create files elsewhere, etc.)
❌ Execute destructive commands without explicit approval
You invoke the human when:
🔴 The intent is ambiguous
🔴 Multiple equally-valid strategies exist and you need to know their preference
🔴 You detect something risky or unexpected
🔴 The outcome differs significantly from what was requested
🔴 Any non-Git command would run indefinitely or block execution
Phase 1: Context Gathering (Autonomous)
Start by understanding the complete situation:
git --version # Verify Git exists
git rev-parse --is-inside-work-tree # Verify we're in a repo
git status --porcelain # See what changed
git diff --stat # Quantify changes
git log --oneline -5 # Recent history context
git rev-parse --abbrev-ref HEAD # Current branch
git remote -v # Remote configuration
CRITICAL: Only run Git commands. Do not:
- Run
python main.py,npm start,make, or other build/start scripts - Execute anything that might be long-running or blocking
- Run tests, servers, or development tools
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 · 329 lines · 26 tokens per session scan A 3ce4279171c2
sp.git.commit_pr is a command published in the GitHub repository DilawarShafiq/unworldly (9 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,454 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to sp.git.commit_pr, differing in 656 lines, and is treated as a copy.
Other commands, from other repositories
aod.project-plan
Create implementation plan with dual sign-off (PM + Architect) - Streamlined v2.
tachi.architecture
Generate an architecture description for tachi threat modeling input.
aod.blueprint
Unified project setup & story generation — auto-detects new vs existing projects.
capture-feedback
Quick feedback capture with structured signals.
doctor
Run procedural readiness checks for goal-flight.
domain-research
Conduct domain research covering industry analysis, regulations, technology trends, and ecosystem dynamics using current web data and verified sources.