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/abilenduke/copilot-developer/skill-buildernpx skills add ABilenduke/copilot-developer --skill skill-buildergit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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 | $0.00082 | $0.02417 |
| Opus 5 | $0.00041 | $0.01208 |
| Sonnet 5 | $0.00016 | $0.00483 |
| Haiku 4.5 | $0.00008 | $0.00242 |
Grade A, and why
skill-builder 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.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Builder
HARD RULES
These rules are absolute. No exceptions.
Rule 1: ALWAYS walk through discovery
Never generate a skill from a one-line description. Always walk through the interactive phases to understand purpose, scope, and boundaries. Even experienced users benefit from Phase 1 qualification.
Rule 2: NEVER overwrite without confirmation
If a skill directory already exists, STOP and ask: "The skill '{name}' already exists. Do you want to update it or create a different skill?" Never silently overwrite.
Rule 3: ALWAYS register in boost.json
Every domain skill must be added to the skills array in boost.json. Workflow skills invoked via slash commands do not go in boost.json.
Rule 4: ALWAYS check for overlapping skills
Before creating a new skill, compare its scope against every existing skill. If overlap exists, propose merging or boundary clarification before proceeding.
Purpose
This is a meta-skill that builds other skills through interactive Q&A. It ensures every new skill follows project conventions, has proper frontmatter, uses <code-snippet> blocks for code examples, and integrates with boost.json and hook mappings.
Skill Type Classification
Every skill falls into one of three types. Identifying the type early determines the output shape.
| Type | Purpose | Output Shape | Examples |
|---|---|---|---|
| Domain Knowledge | Teaches patterns for a code area | SKILL.md with code snippets, "When to Apply", "Common Pitfalls" | pest-testing, content-publishing, affiliate-tracking |
| Interactive Workflow | Guides multi-step processes | SKILL.md with phases, progress indicator, templates/, examples/ | plan, execute, feature |
| Utility | Cross-cutting conventions | SKILL.md with rules and mapping tables | documentation-maintenance |
Key Differences
- Domain skills go in
boost.json— they auto-activate based on context - Workflow skills are invoked via slash commands — they do NOT go in
boost.json - Utility skills go in
boost.json— they auto-activate like domain skills - Only workflow skills typically need
templates/andexamples/subdirectories - Domain skills embed code patterns inline using
<code-snippet>blocks
What ships with it
5 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.
- yesterday First seen · 252 lines · 82 tokens per session scan A bb0568166c8e
skill-builder is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 82 tokens to every session and 2,417 once invoked, about $0.0004 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.
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…