issue-implement

issue-implement is a skill for Claude Code, Codex from vergil-project/vergil-claude-plugin. It costs 38 tokens per session (2,284 once invoked), scanned A, original, MIT.

A procedure for implementing a GitHub issue from start to finish as the user agent. It changes code in a separate worktree, checks that it works, and prepares the pull-request details for human submission.

In plain words
What is it for?
Build a feature, fix a bug, or start issue work; use sub-agents when useful, run validation, record PR metadata, and hand the result to the human.
Why use it?
It gives an issue a defined path from request to tested implementation while keeping the human in control of opening the pull request.

Skill for Claude CodeCodex

Part of the vergil plugin — 15 skills, 2 agents, 2 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/vergil-project/vergil-claude-plugin/issue-implement
Any agent
npx skills add vergil-project/vergil-claude-plugin --skill issue-implement
Clone the repo
git clone --depth 1 https://github.com/vergil-project/vergil-claude-plugin

Made for: Claude Code, Codex.

Or install vergil, the plugin that ships this one along with the rest of its 15 skills, 2 agents, 2 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 issue-implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/issue-implement.svg)](https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/issue-implement)
Your own site
<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/issue-implement"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/issue-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,284 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.02284
Opus 5 $0.00019 $0.01142
Sonnet 5 $0.00008 $0.00457
Haiku 4.5 $0.00004 $0.00228

Measured 5d ago against content hash ec59ddd74060, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-implement 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 5d 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.

skills/issue-implement/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Implement

Implement a GitHub issue end-to-end as the USER agent, then hand the PR off to the human. You implement the issue directly in a worktree, validate it green, record the PR metadata through vrg-pr-workflow report-ready, and tell the human to open the PR with vrg-submit-pr. You never open the PR yourself.

Execute efficiently — trust and escalate

Implement by the most efficient means at your disposal. Sub-agents are encouraged wherever they make the work faster or keep your context clean — research fan-out, parallel sub-tasks, isolated exploration. You need not narrate every step for the human to watch: oversight lives in the front-loaded plan and at the hard gates (PR submit, merge, release), not in a live transcript. This is the Front-Loaded Judgment, Trusted Execution doctrine (see CLAUDE.md).

The one thing that pulls the human back mid-flight is a problem you cannot resolve: stop and ask rather than thrash or guess. Never fabricate a result and never suppress a validation gate.

Preflight

  1. Confirm you are the USER agent: vrg-whoami --mode must print user. If not, stop — this skill runs in the user-agent session.

  2. Not an operational task. If the issue carries an operational label, stop — it is not code-implementation. An operational task is run, not built: its acceptance is a recorded Outcome: comment, not a PR (and the PR tooling refuses it). Hand a validation issue to issue-validate and a deployment issue to issue-deploy.

  3. Create the worktree for this issue from the repo root and work inside it (pick a 2–4 token kebab slug):

    vrg-git worktree add -b feature/<N>-<slug> .worktrees/issue-<N>-<slug> origin/develop
    cd .worktrees/issue-<N>-<slug>
    

Implement

Implement the issue here with small vrg-commit commits. Validate until green — vrg-container-run -- vrg-validate — fixing every failure and re-running; never suppress a gate.

Read the full file on GitHub · 178 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. 5d ago First seen · 178 lines · 38 tokens per session scan A ec59ddd74060

Subscribe to this mod's changes

issue-implement is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,284 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens