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/researchnpx skills add ABilenduke/copilot-developer --skill researchgit 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 | $0.00095 | $0.03775 |
| Opus 5 | $0.00048 | $0.01887 |
| Sonnet 5 | $0.00019 | $0.00755 |
| Haiku 4.5 | $0.00010 | $0.00378 |
Grade A, and why
research 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Skill
Purpose
This skill handles three distinct research workflows:
- Story Mode (
/research story) — Creates a story directory under a feature, writesbrief.md(business case with RICE scoring and pre-mortem), and creates a GitHub issue (type:story, Backlog). - Context Mode (
/research contextor/research brief) — Scans the codebase and produces a self-contained research brief for external AI deep research tools (Gemini, Perplexity, ChatGPT). This is the evolution of the old/research-briefskill. - Spike Mode (
/research spike) — Creates a time-boxed investigation document with a clear question, findings, recommendation, and next steps.
Pipeline position:
- Story mode:
/research story→/plan→/execute - Context mode:
/research context→ external AI tool (manual) →/plan - Spike mode:
/research spike→ recommendation → story or no action
HARD RULES
These rules are absolute. No exceptions.
Rule 1: NEVER do research yourself (Context Mode only)
In Context Mode, you are a context packager, not a researcher. Your job is to scan the codebase, gather facts, and frame questions. You do NOT answer the research questions, suggest architectures, or recommend packages. The external AI research tool does that. You provide the raw material.
Rule 2: NEVER fabricate codebase details
Every code excerpt, version number, file path, and pattern description MUST come from actually reading the codebase. If you can't find something, say it doesn't exist. Never invent model relationships, guess at config values, or assume a file's contents.
Rule 3: Structural contracts inline, behavioral implementation summarized (Context Mode)
Inline as actual code (structural contracts):
- Model relationships, casts, traits (10-20 lines per model)
- Migration schema (column names, types, indexes)
- Pattern exemplar key files (service class, job chain, controller)
- Route definitions for the relevant area
- TypeScript type definitions and interfaces
What ships with it
4 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 · 364 lines · 95 tokens per session scan A c443d9c7d938
research is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 95 tokens to every session and 3,775 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.
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…