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/jnarowski/agentcmd/create-prgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.01052 |
| Opus 5 | $0.00007 | $0.00526 |
| Sonnet 5 | $0.00003 | $0.00210 |
| Haiku 4.5 | $0.00001 | $0.00105 |
Grade A, and why
create-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 today.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Pull Request
Commits all changes, pushes the current branch to remote, and creates a GitHub pull request with an AI-generated description. Automatically analyzes git diff to generate PR title and body if not provided.
Variables
- $title: $1 - PR title and commit message (optional - AI generates from git diff if not provided)
Instructions
- Analyze git changes to understand what was modified, added, or removed
- Generate concise, conventional commit-style title if not provided (e.g., "feat: add user auth", "fix: resolve memory leak")
- Generate PR body summarizing key changes, files affected, and purpose
- Commit message uses the title (provided or generated)
- Always push to remote before creating PR
- PR always targets
mainbranch as base - Return structured JSON response with PR URL and metadata
Workflow
-
Analyze Changes
- Run
git statusto see all changes (staged and unstaged) - Run
git diff HEADto see all modifications - Run
git branch --show-currentto get current branch name - Understand what files changed and why
- Run
-
Generate Title (if not provided)
- If $title not provided, analyze diff and generate conventional commit title
- Format:
type: brief description(e.g., "feat: implement user settings", "fix: handle null pointer") - Types: feat, fix, docs, refactor, test, chore
- Keep under 72 characters
-
Generate PR Body
- Summarize changes in 2-4 bullet points
- Focus on what changed and why
- Include key files or components affected
- Keep concise and actionable
-
Commit and Push
- Run
git add -Ato stage all changes - Check if there are changes to commit with
git status --porcelain - If changes exist: Run
git commit -m "$title"using title from step 2 - If no changes: Skip commit (already committed previously)
- Capture commit SHA from
git rev-parse HEAD - Run
git push -u origin <branch-name>(works even if already pushed) - Only fail if git commands return errors (not if nothing to commit)
- Run
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.
- today First seen · 108 lines · 14 tokens per session scan A ec252e748cad
create-pr is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 1,052 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 2026-09-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.