vajra-prepare-pr

vajra-prepare-pr is a skill for Claude Code, Codex from zamana-inc/vajra. It costs 35 tokens per session (1,472 once invoked), scanned A, original, MIT.

A workflow for preparing completed code for a pull request, which is a proposed code change for review. It checks readiness, tests the code, reviews the actual Git diff, creates the commit, and pushes the branch, without changing GitHub directly.

In plain words
What is it for?
Use it after implementation and review findings are addressed to validate the work, prepare Git history, push the branch, and provide any manual steps needed.
Why use it?
It helps prevent unfinished or untested work from being sent for review and gives reviewers a concise explanation of the change and test evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after implementation and review findings are addressed to validate the work, prepare Git history, push the branch, and provide any manual steps needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zamana-inc/vajra/vajra-prepare-pr
Install

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.

Any agent
npx skills add zamana-inc/vajra --skill vajra-prepare-pr
Clone the repo
git clone --depth 1 https://github.com/zamana-inc/vajra

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vajra-prepare-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-prepare-pr/github.svg)](https://agentmods.dev/skills/zamana-inc/vajra/vajra-prepare-pr)
Your own site
<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-prepare-pr"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-prepare-pr/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.

agentmods 80×15 button for vajra-prepare-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/zamana-inc/vajra/vajra-prepare-pr"><img src="https://agentmods.dev/badge/skills/zamana-inc/vajra/vajra-prepare-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01472
Opus 5 $0.00017 $0.00736
Sonnet 5 $0.00007 $0.00294
Haiku 4.5 $0.00003 $0.00147

Measured 13d ago against content hash 9b79ebe2e5ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vajra-prepare-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 13d 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.

orchestrator/skills/vajra-prepare-pr/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vajra Prepare PR

You are shipping the work. Take completed, validated code and turn it into a pull request that an engineer can review and approve in under 5 minutes.

Context

PR reviewers are busy engineers who want to merge fast. Your PR should make that easy: clear title, concise body, real test evidence. No fluff.

Vajra runs as an automated agent. If the implementation requires manual steps (like a database migration), include a clear "Manual Steps" section in the PR body so the reviewing engineer knows exactly what to run.

Mindset

A PR is a communication artifact. Its purpose is to help a reviewer understand what changed, why, and how it was verified — so they can approve quickly.

The body is not a retelling of the plan or a log of your process. It is a concise description of what this PR does, how it was tested, and anything the reviewer should know. Respect their time.

Process

1. Verify readiness

Before creating git artifacts:

  • Check that the review approved or findings were addressed
  • Run tests (do not assume — verify)

If not ready — tests fail, findings unaddressed — stop. Do not create a PR for broken code.

2. Inspect the actual diff

git diff is the truth. Verify:

  • Diff matches the issue's intent
  • No debug code, temp files, or unrelated changes
  • No secrets in the diff

3. Write the PR title

Specific and descriptive. Start with the issue identifier.

  • Good: "ENG-142: Add email validation to user creation endpoint"
  • Bad: "Fix bug", "Update backend", "ENG-142"

4. Write the PR body

Three sections, plus Manual Steps if needed:

Summary: what this PR does in concrete terms. What files changed, what behavior is different. 3-5 bullet points, not paragraphs.

Testing: validation commands and results. Real output, not "all tests pass."

Manual Steps (if needed): database migrations, config changes, or deployment steps that a human engineer must perform. Be specific — include the migration description, new columns, indexes, etc.

Read the full file on GitHub · 146 lines

Changes

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.

  1. 13d ago First seen · 146 lines · 35 tokens per session scan A 9b79ebe2e5ed

Subscribe to this mod's changes

vajra-prepare-pr is a skill published in the GitHub repository zamana-inc/vajra (55 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,472 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 2026-08-30.