lfg

lfg is a skill for Claude Code, Codex from psd401/psd-claude-plugins. It costs 62 tokens per session (3,793 once invoked), scanned B, original, MIT.

An autonomous workflow for taking a software change from implementation through a fully checked and reviewed pull request. A pull request is a proposed code change submitted for review, and CI is automated testing run by the repository.

In plain words
What is it for?
Implementing a change, running builds and tests, checking browser behavior with Playwright, attaching screenshots, opening a pull request, monitoring review and CI results, and fixing reported problems.
Why use it?
It reduces the need to coordinate implementation, testing, visual checks, review responses, and CI fixes manually.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the psd-coding-system plugin — 9 skills, 5 hooks shipped together

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/psd401/psd-claude-plugins/lfg
Any agent
npx skills add psd401/psd-claude-plugins --skill lfg
Clone the repo
git clone --depth 1 https://github.com/psd401/psd-claude-plugins

Made for: Claude Code, Codex.

Or install psd-coding-system, the plugin that ships this one along with the rest of its 9 skills, 5 hooks.

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 lfg

README.md
[![agentmods](https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/lfg.svg)](https://agentmods.dev/skills/psd401/psd-claude-plugins/lfg)
Your own site
<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/lfg"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/lfg.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,793 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.03793
Opus 5 $0.00031 $0.01896
Sonnet 5 $0.00012 $0.00759
Haiku 4.5 $0.00006 $0.00379

Measured 3d ago against content hash 520a97f1202f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

lfg scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -qxF '.claude/worktrees/' .git/info/exclude 2>/dev/null || echo '.claude/worktrees/' >> .git/info/exclude
plugins/psd-coding-system/skills/lfg/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LFG — Autonomous Build-to-Done

You implement a change and drive it all the way to a clean, fully-reviewed PR: implement → verify the Definition of Done → open a PR with screenshots → watch CI and the AI reviewers and fix every finding, round after round, until everything is green. You do not stop at "ready for review." You stop when the PR is 100% clean.

This skill absorbs the old /work, /test, /debug, /optimize, /review-pr, and /security-audit.

Target: $ARGUMENTS

Contracts: docs/patterns/definition-of-done.md, docs/patterns/issue-contract.md.

No deferral

Fix everything now. A failing test, a lint warning, a reviewer finding — each gets fixed in this session, not deferred to a TODO or follow-up issue, and never suppressed with eslint-disable / # noqa / @ts-ignore. Finish the whole task, not just the easy part of it — report completion only when the DoD is fully green. The one exception: a fix genuinely blocked by an external constraint (an API you don't control, a separate deploy pipeline) — surface that with AskUserQuestion instead of working around it.

Phase 1: Work type + Definition of Done

if [[ "$ARGUMENTS" =~ ^[0-9]+$ ]]; then
  WORK_TYPE="issue"; ISSUE_NUMBER=$ARGUMENTS
  gh issue view $ISSUE_NUMBER
  gh issue view $ISSUE_NUMBER --comments
  ISSUE_BODY=$(gh issue view $ISSUE_NUMBER --json body --jq '.body')
else
  WORK_TYPE="quick-fix"; ISSUE_NUMBER=""; ISSUE_BODY="$ARGUMENTS"
fi

Load the DoD — extract the block between <!-- dod:start --> and <!-- dod:end --> from the issue body. If absent (quick fix or non-contract issue), generate a DoD from the canonical list in definition-of-done.md + the project's .psd/verify.json. This is your loop exit condition; restate it explicitly before coding.

Phase 2: Branch — auto-isolated worktree (parallel-safe)

By default /lfg runs each issue in its own git worktree and switches this session into it, so you can open several Claude windows in the same repo, run /lfg <issue> in each, and they never collide. Opt out with auto_worktree: false in .psd/verify.json (branch in place instead). Auto-worktree is skipped automatically when the session is already inside a worktree.

Read the full file on GitHub · 243 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. 3d ago First seen · 243 lines · 62 tokens per session scan B 520a97f1202f

Subscribe to this mod's changes

lfg is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 3,793 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…

Azure/azure-sdk-for-net · 192 tokens

requirements-author

Requirements authoring guide for BRD and PRD across Discover, Define, and Govern with canonical templates and handoff contracts.

microsoft/hve-core · 27 tokens

mps-aspect-actions

Use when defining or editing MPS node factories (the "actions" aspect) — NodeFactories roots, per-concept NodeFactory setup functions that initialize a freshly created node and optionally copy data from a replaced sampleNode, plus the actions aspect's CopyPasteHandlers and PasteWrappers roots. Reach for this skill…

JetBrains/MPS · 115 tokens

devtools-event-client

Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…

TanStack/devtools · 79 tokens

api-design

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

majiayu000/spellbook · 42 tokens

crypto-market-rank

Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…

tradecatlabs/tradecat-public · 85 tokens