experimental-pr-workflow

experimental-pr-workflow is a skill for Claude Code from adrielp/ai-engineering-harness. It costs 48 tokens per session (1,105 once invoked), scanned A, original, Apache-2.0.

A workflow for turning experimental code changes into documented tickets and reviewable pull requests. A pull request is a proposed set of changes submitted for review before merging.

In plain words
What is it for?
Use it when commits lack tickets, when someone mentions founder mode, or when exploratory work needs to be documented and formalized.
Why use it?
It adds project tracking and review context after work was done quickly without the usual ticketing process.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when commits lack tickets, when someone mentions founder mode, or when exploratory work needs to be documented and formalized.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adrielp/ai-engineering-harness/experimental-pr-workflow
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 adrielp/ai-engineering-harness --skill experimental-pr-workflow
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

Made for: Claude Code.

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 experimental-pr-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/experimental-pr-workflow.svg)](https://agentmods.dev/skills/adrielp/ai-engineering-harness/experimental-pr-workflow)
Your own site
<a href="https://agentmods.dev/skills/adrielp/ai-engineering-harness/experimental-pr-workflow"><img src="https://agentmods.dev/badge/skills/adrielp/ai-engineering-harness/experimental-pr-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 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 $0.00048 $0.01105
Opus 5 $0.00024 $0.00553
Sonnet 5 $0.00010 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured 8d ago against content hash 011318d8b435, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

experimental-pr-workflow 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude/skills/experimental-pr-workflow/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experimental PR Workflow

When to Use This Skill

Activate this skill when:

  • User mentions "founder mode" or references rapid experimentation
  • User has made commits without associated tickets
  • User asks to "formalize experimental work" or "create ticket for this"
  • You detect commits on a feature branch without ticket references
  • User asks to "clean up" or "properly document" exploratory work

This skill helps transition from rapid prototyping to proper workflow hygiene.

The Problem This Solves

Sometimes you need to move fast and experiment without the overhead of creating tickets and planning docs first. This is great for exploration, but eventually you need to:

  1. Document what you built and why
  2. Create a proper ticket for tracking
  3. Get the work into a reviewable PR
  4. Follow the team's standard workflow

This skill handles that transition retroactively.

Core Process

Step 1: Verify Commit Exists

Check recent commits:

git log --oneline -5

If no recent commits, help create one first or review current changes.

Step 2: Understand What Was Built

Gather context from the commit:

git show --stat HEAD
git show HEAD

Analyze the changes:

  • What files were modified?
  • What functionality was added/changed?
  • What problem does this solve?
  • What technical decisions were made?

Step 3: Create Ticket (if using a ticket system)

Create a ticket describing the work:

## Problem to Solve
[Describe the user need or pain point from a user perspective]

## Proposed Solution
[Describe what you implemented]
[Explain the technical approach taken]

## Implementation Notes
- [Key file/component modified]
- [Technical decision made]

## References
- Commit: [SHA]
- Branch: [current branch name]

Important: You MUST gather a "Problem to Solve" - don't just document implementation.

Step 4: Create Proper Git Branch

Ensure you're on main first:

git checkout main

Create the new branch with proper naming:

git checkout -b [TICKET-ID]-[description]

Read the full file on GitHub · 185 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. 8d ago First seen · 185 lines · 48 tokens per session scan A 011318d8b435

Subscribe to this mod's changes

experimental-pr-workflow is a skill published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,105 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.