A read-only status checker for an issue-to-pull-request workflow. It shows the expected stages and checks the current Git branch and pull-request status using local Git and GitHub information.

Use it to inspect the current branch, whether it has uncommitted or unsynchronised changes, and whether an associated pull request exists or needs review.

It lets you see where work currently stands without changing files, branches, commits, or GitHub data. It also explains what each workflow stage is supposed to do.

workflow — Skill by JustinThomas2

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.

agentmods

npx agentmods add skills/justinthomas2/agentrc/workflow

Any agent

npx skills add JustinThomas2/agentrc --skill workflow

Clone the repo

git clone --depth 1 https://github.com/JustinThomas2/agentrc

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 587 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.00587
Opus 5	$0.00015	$0.00293
Sonnet 5	$0.00006	$0.00117
Haiku 4.5	$0.00003	$0.00059

Measured yesterday against content hash 2aa4507289dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

skills/workflow/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

This skill is read-only. Run only:

git status -sb
gh pr status

Do not branch, commit, push, post comments, edit files, or run mutating GitHub commands.

Pipeline Map

Print this compact map first, one line per skill:

file-issue: rough idea -> GitHub issue draft or filed issue; stops before filing for approval.
work-issue: issue number -> local branch with committed implementation; stops before push or PR.
open-pr: issue number -> pushed branch and opened PR; stops after reporting the PR URL.
review-pr: PR number -> posted review feedback comment; stops before posting for approval.
address-feedback: PR number -> committed review fixes; stops before push or reviewer replies.
respond-feedback: PR number -> posted approved reviewer replies; ends the workflow.

State Detection

Use git status -sb to identify:

current branch
whether the branch is ahead of, behind, or diverged from its upstream
whether there are uncommitted changes

Use gh pr status to identify:

whether the current branch already has a PR
the PR number when present
whether the visible review decision is approved, changes requested, or review required

Then print:

You are here: one concise sentence describing the current state.
Next: the exact next skill invocation.

Choose the next invocation this way:

On main with no feature branch context: file-issue with the rough idea.
On a non-main branch with uncommitted changes: finish or discard the local changes before invoking another pipeline skill.
On a non-main branch with commits ahead of main and no PR: open-pr with issue N. Infer N from a branch segment like 16 in refactor/16-workflow-skill-names; if no issue number is clear, say that the issue number is needed.
On a branch with an open PR and no review decision yet: review-pr with PR N to review it, or wait for an external review.
On a branch with an open PR and changes requested: address-feedback with PR N.
After review-fix commits are ready on a PR branch: respond-feedback with PR N once the fixes have been pushed and reviewed by Justin.
If the state is ambiguous, say what is missing instead of guessing.

Read the full file on GitHub · 58 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.

yesterday First seen · 58 lines · 30 tokens per session scan A 2aa4507289dc

Subscribe to this mod's changes

workflow is a skill published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 587 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 2026-08-31.

Code review Git and workflow Productivity

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens