A router for a set of development skills. It recommends the next step in a workflow from breaking a GitHub issue into smaller pieces through implementation, debugging, code review, and post-merge cleanup.

Use it to select workflows for issue decomposition, implementation with TDD, bug diagnosis, review fixes, worktrees, and cleanup after merging.

It helps choose the appropriate development procedure instead of guessing which skill to run next. It directs work but does not perform the work itself.

flow — Skill for Claude Code by YoungjaeDev/my-claude-plugins

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 YoungjaeDev/my-claude-plugins --skill flow

Clone the repo

git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/flow/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/flow)

Your own site

<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/flow"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/flow/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/flow"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,124 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.

Model	Per session	Once invoked
Fable 5.1	$0.00209	$0.01124
Opus 5.5	$0.00084	$0.00450
Sonnet 5.5	$0.00042	$0.00225
Haiku 4.5	$0.00021	$0.00112

Measured 23d ago against content hash a89e002d6915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flow 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 23d 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.

plugins/dev/skills/flow/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dev flow

A short router, not a skill that does the work itself. Matt's skills (mattpocock-skills) own the front half, from idea to a PR ready for review; dev owns the back half, from that PR to merge and cleanup.

The flow

[Matt] /grill-with-docs → /to-spec → /to-tickets    in one context window, no /compact in between
[Matt] /implement-spec ("open a draft PR" gives one PR) or /implement per ticket (/clear between tickets)
── when there is a PR ──
[dev]  /dev:review-loop → merge → /dev:post-merge → /retro [Matt] in the session that built it
[dev]  /dev:release when needed

Front half. For anything this block does not answer (context management, the prototype and wayfinder branches, which Matt skill fits an odd request), ask /ask-matt. This router keeps no copy of Matt's rules, so it cannot go stale against them.
Back half. /dev:review-loop loops CodeRabbit + Codex review to convergence; /dev:post-merge cleans up the branch and tracking after the merge; /retro turns what went wrong into automated checks.

Branches

Bug. /diagnosing-bugs → /retro.
No PR. Skip the back half.
Ad-hoc parallel work without a spec. /dev:orchestrate. A spec's tickets go through /implement-spec instead.
Small request, but ambiguous. /docs:interview-methodology.
An original arrives (meeting notes, research, a customer or vendor document). /wiki:ingest; it creates the wiki on first use. Asking what that knowledge says. /wiki:query.
Worktree. /dev:post-merge runs from inside a worktree too: it operates on the main repo throughout and prints one cleanup line (git worktree remove plus the branch delete) as its last step instead of trying to remove itself.
Non-default base. /dev:review-loop detects a PR base that is not the default branch and posts @coderabbitai review itself on every push (unless the repo disabled auto-review), because CodeRabbit's own auto-review only covers the default branch plus base_branches.
Playwright E2E. /dev:e2e-setup once per repo (harness + CI). /dev:e2e-author per critical user flow. /dev:e2e-debug when a CI E2E run fails or flakes.

Read the full file on GitHub · 56 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.

23d ago Changed · -1 tokens per session a89e002d6915
25d ago Changed · +22 lines · +52 tokens per session b3c78453a3b9
1mo ago Changed 15fa621bbd39
1mo ago First seen · 34 lines · 158 tokens per session scan A 365f02874719

Subscribe to this mod's changes

flow is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 209 tokens to every session and 1,124 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-19.

Git and workflow Planning

flow

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

dev flow

The flow

Branches

What this file has done since we first saw it

Other skills, from other repositories

merge-batch

prowler-commit

gh-auth-isolation

comet-github

github-skill

release-helper