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.
npx agentmods add skills/syi0808/screenize/github-plannernpx skills add syi0808/screenize --skill github-plannergit clone --depth 1 https://github.com/syi0808/screenizeWhat 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 | $0.00056 | $0.00712 |
| Opus 5 | $0.00028 | $0.00356 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
github-planner 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GITHUB ISSUE IMPLEMENTATION PLANNER
Fetch a GitHub issue, analyze its requirements, explore the relevant codebase, and produce a comprehensive implementation plan.
When to use: Execute /plan-issue with a GitHub issue URL or number to generate an implementation plan before starting work.
Step 1: Fetch Issue
Run the fetch script to retrieve issue details:
uv run .claude/skills/github-planner/scripts/fetch_issue.py <issue_url_or_number>
Accepts:
- Full URL:
https://github.com/owner/repo/issues/123 - Short URL:
owner/repo#123 - Issue number (uses current repo):
123or#123
The script outputs structured JSON with title, body, labels, comments, and metadata.
Step 2: Analyze Issue
Parse the fetched issue content and identify:
- Problem statement - What needs to be solved
- Proposed solution - If described in the issue
- Acceptance criteria - Explicit or inferred requirements
- Scope boundaries - What is and isn't included
Step 3: Explore Codebase
Based on the analysis, explore relevant parts of the codebase:
- Use Glob/Grep to find files related to the issue's domain
- Read key files to understand current architecture
- Identify integration points and dependencies
- Check for existing patterns that the implementation should follow
- Reference
CLAUDE.mdfor project architecture and conventions
Step 4: Generate Implementation Plan
Write the plan to private-docs/plans/<issue-number>-<slug>.md using the template:
uv run .claude/skills/github-planner/scripts/create_plan.py \
--issue <number> \
--title "<issue-title-slug>"
Fill the generated template with:
- Overview: Issue summary and goals
- Architecture Analysis: How changes fit into existing architecture
- Implementation Steps: Ordered tasks with specific file changes
- Files to Modify/Create: Exhaustive list with descriptions
- Risk Assessment: Potential issues, edge cases, breaking changes
- Testing Strategy: How to verify the implementation
What ships with it
3 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.
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.
- 2d ago First seen · 98 lines · 56 tokens per session scan A c6a9ae9d88bf
github-planner is a skill published in the GitHub repository syi0808/screenize (602 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 712 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…