What is implement-tickets?

A workflow for implementing a selected queue of work items, such as tickets or issues, using isolated workers and review steps. A worktree is a separate working copy that lets changes be developed without disturbing other work.

Use it to implement selected, ranged, queried, or dependency-linked backlog items. It covers choosing a work source and worker harness, assigning vertical slices, reviewing results, and managing merges.

It coordinates dependent tasks while keeping each change isolated and reviewable. It also provides a way to monitor workers and control when changes are merged.

implement-tickets — Skill for Codex by AnthonyPoschen: A workflow for implementing a selected queue of work…

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/anthonyposchen/agent-skills/implement-tickets

Any agent

npx skills add AnthonyPoschen/agent-skills --skill implement-tickets

Clone the repo

git clone --depth 1 https://github.com/AnthonyPoschen/agent-skills

Made for: Codex.

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/anthonyposchen/agent-skills/implement-tickets.svg)](https://agentmods.dev/skills/anthonyposchen/agent-skills/implement-tickets)

Your own site

<a href="https://agentmods.dev/skills/anthonyposchen/agent-skills/implement-tickets"><img src="https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/implement-tickets.svg" alt="Measured on agentmods" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,393 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 5.1	$0.00094	$0.02393
Opus 5	$0.00047	$0.01196
Sonnet 5	$0.00019	$0.00479
Haiku 4.5	$0.00009	$0.00239

Measured yesterday against content hash 6fee4f5adc68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

implement-tickets 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/implement-tickets/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Tickets

Use this skill to deliver a selected dependency-linked work-item queue safely. It is an orchestration workflow, not a shortcut around the project implementation workflow: every worker implements one vertical slice only.

Read project setup and discovery, then read the core workflow before scheduling work. Select and read one work-source adapter and one harness adapter before the first tracker or worker action:

For harnesses that already provide agents, sandboxes, or progress UI, read the capability contract. Use only the supervisor capabilities that add durable or deterministic behavior.

Codex and Grok can run the manager loop directly. Codex isolates workers with codex exec. Grok isolates workers with background spawn_subagent and keeps reviews moving with monitors plus a scheduled poll. OpenCode needs the bundled Go supervisor to provide durable state and process management. Build scripts/orchestrate.go for OpenCode and for any environment where the chat session cannot safely own a long-running loop. The supervisor uses only the Go standard library and does not launch Grok subagents. If no adapter fits, inspect the repository and write the missing adapter contract before starting work.

Start Safely

Read project instructions, domain documentation, applicable decisions, and the project work-item conventions.
Follow the project's AGENTS.md reference chain. Load .github/implement-tickets.json when present. If required settings remain ambiguous, stop preflight and ask the bundled setup questions together.
Inspect the target branch, primary checkout, existing isolated checkouts, active workers, open reviews, and candidate work items.
Refuse to start when the primary worktree has unrelated uncommitted changes. Never reset, clean, or overwrite another person's work.
Confirm the manager has standing authority to push branches, post review comments, and close leftover open items after verified integration. Only a human may merge. If the host denies one of those writes, report the pending action immediately.
Select an isolated checkout location and concurrency cap. Default to three; a smaller ready set naturally lowers concurrency. Do not launch an unbounded backlog merely because many items appear ready.
Select the provider/model for the chat manager and the provider/model for background workers. Apply the selected harness defaults unless the user overrides them. State both roles, models, and reasoning levels in the first start message. Preserve existing harness provider settings. Do not add provider restrictions unless the user explicitly requests them.
For OpenCode, initialize and start the bundled supervisor before launching workers, then keep the chat session on events --follow or status. For Codex or Grok, run the manager loop in this chat session. Use the same supervisor for durable state when unattended operation is requested; Grok still launches its own workers.

Read the full file on GitHub · 189 lines

Files

What ships with it

14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed · +7 lines 6fee4f5adc68
5d ago First seen · 182 lines · 94 tokens per session scan A 33fd244e39be

Subscribe to this mod's changes

implement-tickets is a skill published in the GitHub repository AnthonyPoschen/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 2,393 once invoked, about $0.0005 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.

Git and workflow Project management

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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