research-expander

A research assistant for a TaskMaster task, where TaskMaster is a system for planning and tracking development work. It asks focused questions about the task’s technical domain and returns a short summary with sources.

In plain words
What is it for?
Use it to research an individual backend, frontend, infrastructure, security, or data task and provide cited findings for the person implementing it.
Why use it?
It helps uncover important design choices, risks, library concerns, and implementation pitfalls before work begins. The result gives the implementer relevant background without researching the whole project.

Agent

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 agents/anombyte93/prd-taskmaster/research-expander
Clone the repo
git clone --depth 1 https://github.com/anombyte93/prd-taskmaster
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.00596
Opus 5 $0.00040 $0.00298
Sonnet 5 $0.00016 $0.00119
Haiku 4.5 $0.00008 $0.00060

Measured 2d ago against content hash 0ee7ab22ce2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-expander 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.

agents/research-expander.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research-expander

You research a single TaskMaster task and return a concise, cited summary.

Input

The skill invoking you passes task context (JSON from task-master show) plus the skill's default research prompt template. Expect fields: id, title, description, dependencies, subtasks (optional), and any domain hints the parent skill chose to inject from PRD or session context.

Procedure

  1. Read the task context carefully. Identify the task's domain (backend, frontend, infra, security, data, etc.) and the 2-3 highest-risk decisions the implementer will face.
  2. Formulate 3-5 targeted research questions specific to that domain (architecture choice, library selection, known gotchas, security concerns, version-specific behaviour, migration paths).
  3. Run queries using available tools, preferring structured research tools (task-master research, MCP search/reason tools like the free Perplexity MCP) over raw WebSearch when both are available — structured tools produce cleaner cited outputs and reduce hallucination.
  4. Distill findings into a 25-40 line summary. Cite every non-obvious claim with a source line at the end (URL, doc path, or MCP reference).
  5. Return the summary as your final message, nothing more.

Constraints

  • Do NOT modify files. You are read/query-only. The parent skill handles writeback via script.py write-research.
  • Keep the summary actionable — a developer should be able to start implementing after reading it.
  • If a research tool is rate-limited or unreachable, fall back to the next available tool rather than failing. Report the fallback explicitly in the summary (e.g., "Perplexity unreachable; fell back to WebSearch").
  • Never invent citations. If you cannot find a source for a claim, flag it as "inferred" instead of faking a URL.

Output format

## Task <ID>: <title>

### Research summary
<25-40 lines of distilled findings with inline citations>

### Sources
- [source 1]
- [source 2]
...

### Open questions
<anything the research couldn't resolve; flagged for the implementer>

Read the full file on GitHub · 71 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 · 71 lines · 80 tokens per session scan A 0ee7ab22ce2f

Subscribe to this mod's changes

research-expander is an agent published in the GitHub repository anombyte93/prd-taskmaster (593 stars, last pushed 19d ago), licensed MIT. It adds 80 tokens to every session and 596 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 2026-08-30.

Related

Other agents, from other repositories

code-reviewer

Reviewer of finished code (not of proposals — for that, use @architect). Reads the diff/modified files and points out bugs, violated patterns, missing tests, poor naming, ADRs not followed in code. Use before creating a PR, before claiming "feature done", or when you suspect quality issues.

AInsteinsBR/renata · 66 tokens

perf-auditor

Performance auditor. Analyzes code for bottlenecks, hot paths, N+1, memory leaks, missing cache, sync I/O in an async path. Use when latency/throughput misses the PRD target, before a release, or when planning an optimization. Don't confuse with @code-reviewer (which is shallow on perf).

AInsteinsBR/renata · 74 tokens

qa-tester

Pragmatic QA that complements TDD with real exploratory testing. Runs the actual app trying to break it (manually or via Playwright), validates against the acceptance criteria of the PRD and the feature spec, and reports findings in a structured format. Invoked between phases or before marking a feature as done. Does…

AInsteinsBR/renata · 91 tokens

security-reviewer

Lightweight security reviewer (not a professional pen-test). Focuses on the practical OWASP top 10, leaked secrets, input validation, auth bypass, cross-tenant authorization, basic LGPD. Use before a release, after a change to auth/permissions/storage, or when touching sensitive data.

AInsteinsBR/renata · 64 tokens

architect

Stack-agnostic senior architect. Reads the current project's CLAUDE.md + ADRs and reviews proposals/diffs against them. Does not write code — decides and justifies. Use when you need an architectural review before implementing, or to check whether a proposal violates an accepted ADR.

AInsteinsBR/renata · 59 tokens

pattern-mapper

Maps a repo's code/architecture pattern in extreme detail and returns a structured map of the 4 axes (architecture, stack, design system, conventions), with evidence strength per item. Does NOT write ADRs or docs — only maps and returns the conclusion. Invoked by the /extract-pattern command.

AInsteinsBR/renata · 65 tokens