research

A research workflow for Aha Loop development stories. It investigates unfamiliar libraries, technical approaches, and implementation choices, then records the findings for later work.

In plain words
What is it for?
Use it before building a story that names unfamiliar dependencies or architectural choices, to produce a research report and update the project's knowledge base.
Why use it?
It reduces the risk of making implementation decisions without understanding the relevant tools, documentation, or alternatives.

Skill for Claude CodeCodex

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/youglin-dev/aha-loop/research
Any agent
npx skills add YougLin-dev/Aha-Loop --skill research
Clone the repo
git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,055 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.02055
Opus 5 $0.00019 $0.01027
Sonnet 5 $0.00008 $0.00411
Haiku 4.5 $0.00004 $0.00205

Measured 2d ago against content hash 550a49da6e61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://crates.io/api/v1/crates/tokio" | jq '.crate.max_stable_version'
.agents/skills/research/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research Skill

Conduct thorough technical research before implementation to ensure high-quality, informed decisions.

Workspace Mode Note

When running in workspace mode, all paths are relative to .aha-loop/ directory:

  • Research reports: .aha-loop/research/ (not scripts/aha-loop/research/)
  • Knowledge base: .aha-loop/knowledge/ (not knowledge/)
  • Vendor directory: .aha-loop/.vendor/ (not .vendor/)

The orchestrator will provide the actual paths in the prompt context.


The Job

  1. Identify research topics from the current story's researchTopics field
  2. Fetch third-party library source code if needed
  3. Search documentation and best practices
  4. Analyze and compare alternatives
  5. Generate a research report
  6. Update knowledge base with findings
  7. Mark researchCompleted: true in prd.json

Research Process

Step 1: Identify What to Research

Read the current story from prd.json and extract:

  • researchTopics - explicit topics to investigate
  • Dependencies mentioned in acceptance criteria
  • Patterns referenced in the description

Also check:

  • Previous story's learnings field for follow-up research needs
  • knowledge/project/gotchas.md for related known issues

Step 2: Fetch Library Source Code (If Needed)

For any third-party library research, fetch the source:

# Fetch specific library
./scripts/aha-loop/fetch-source.sh rust tokio 1.35.0

# Or fetch all project dependencies
./scripts/aha-loop/fetch-source.sh --from-deps

After fetching, the source will be at .vendor/<ecosystem>/<name>-<version>/


Library Version Selection

Always Prefer Latest Stable Versions

When researching or recommending libraries, always check for and prefer the latest stable version unless there's a specific compatibility reason not to.

Version Research Process

  1. Query the package registry for latest version:

    # Rust (crates.io)
    curl -s "https://crates.io/api/v1/crates/tokio" | jq '.crate.max_stable_version'
    
    # Or use cargo
    cargo search tokio --limit 1
    
    # Node.js (npm)
    npm view react version
    
    # Python (PyPI)
    pip index versions requests 2>/dev/null | head -1
    

Read the full file on GitHub · 340 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.

  1. 2d ago First seen · 340 lines · 39 tokens per session scan A 550a49da6e61

Subscribe to this mod's changes

research is a skill published in the GitHub repository YougLin-dev/Aha-Loop (181 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 2,055 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

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