A GitHub filing tool that turns roadmap phases or specifications into milestones and issues. A milestone groups related issues, while an issue tracks one task or slice of work.

Use it to file work from a roadmap, phase document, or feature specification, then write the resulting issue numbers back into those planning files.

It removes the manual work of copying planning details into GitHub and keeps issue titles, labels, dependencies, verification steps, and acceptance criteria consistent.

issues — Skill for Claude Code and Codex by 0xrafasec: A GitHub filing tool that turns roadmap phases or…

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/0xrafasec/ai-workflow/issues

Any agent

npx skills add 0xrafasec/ai-workflow --skill issues

Clone the repo

git clone --depth 1 https://github.com/0xrafasec/ai-workflow

Made for: Claude Code, 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/0xrafasec/ai-workflow/issues.svg)](https://agentmods.dev/skills/0xrafasec/ai-workflow/issues)

Your own site

<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/issues"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/issues.svg" alt="Measured on agentmods" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,828 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	$0.00104	$0.04828
Opus 5	$0.00052	$0.02414
Sonnet 5	$0.00021	$0.00966
Haiku 4.5	$0.00010	$0.00483

Measured 4d ago against content hash 083b5fab7614, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issues 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 4d 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/issues/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File GitHub milestones and issues for: $ARGUMENTS

What this skill does

/issues is the hand-off between planning artifacts (docs/roadmap/*.md, docs/specs/*.md) and GitHub. It files:

One milestone per phase — Phase NNN — <phase-name>
One issue per task/slice — title [NNN.N] <task-name> for a roadmap task, [NNN.N.N] <slice-name> for a sliced sub-task, or [<feature>.NNN] <slice-name> for a standalone spec's slice.
Labels per issue — type:<type>, complexity:<low|med|high>, mvp or post-mvp (if derivable), and needs-spec / spec-ready / blocked as appropriate.
Issue body — spec link, file list, dependencies, verification command, feature flag, acceptance criteria pulled from the spec.

After filing, /issues writes the issue numbers back into the source Issue: / Issues: columns so /feature can read them when building branch names.

Parse arguments

The argument is one of:

Roadmap index — /issues docs/roadmap/README.md files everything: one milestone per phase file, one issue per task, one issue per slice where a task points at a sliced spec.
Phase file — /issues docs/roadmap/NNN_<phase>.md files one milestone + the phase's tasks (and slices where applicable).
Sliced spec index — /issues docs/specs/NNN_<feature>/README.md files one issue per row in the Slices table. Uses the feature's existing milestone if found (matched by phase reference in the spec), otherwise creates a standalone no-milestone batch.
Single spec — /issues docs/specs/NNN_<feature>.md files one issue. No milestone unless the spec references a phase.

No argument? Default to docs/roadmap/README.md if it exists; otherwise prompt.

Transport: GitHub MCP first, `gh` fallback

Prefer the GitHub MCP (tool names starting with mcp__github__* or similar) for every read and write. It gives structured JSON in/out and avoids shelling out.

Detection order at skill start:

If mcp__github__* tools are available in this session, use them. Call mcp__github__authenticate (or the equivalent) first if the server reports unauthenticated. If the MCP tool list includes create/update/list tools for issues, milestones, and labels, run the entire skill through MCP.
If GitHub MCP is not available, or a specific action isn't exposed by the MCP, fall back to the gh CLI. Run gh auth status once; if it fails, tell the user to run gh auth login (their call — don't do it for them) and stop.
Never mix mid-run for the same action type. Pick one transport per session; if you start on MCP and hit a missing tool, switch everything remaining to gh rather than interleaving.

Read the full file on GitHub · 255 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.

4d ago First seen · 255 lines · 104 tokens per session scan A 083b5fab7614

Subscribe to this mod's changes

issues is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 4,828 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.

Planning

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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