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.
git clone --depth 1 https://github.com/anombyte93/prd-taskmasterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/anombyte93/prd-taskmaster/research-expander)<a href="https://agentmods.dev/agents/anombyte93/prd-taskmaster/research-expander"><img src="https://agentmods.dev/badge/agents/anombyte93/prd-taskmaster/research-expander/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/anombyte93/prd-taskmaster/research-expander"><img src="https://agentmods.dev/badge/agents/anombyte93/prd-taskmaster/research-expander.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.00596 |
| Opus 5.5 | $0.00032 | $0.00238 |
| Sonnet 5.5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
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 1mo 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 — 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
- 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.
- Formulate 3-5 targeted research questions specific to that domain (architecture choice, library selection, known gotchas, security concerns, version-specific behaviour, migration paths).
- 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. - 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).
- 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>
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.
- 1mo ago First seen · 71 lines · 80 tokens per session scan A 0ee7ab22ce2f
research-expander is an agent published in the GitHub repository anombyte93/prd-taskmaster (607 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 596 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
cs-guardian
Customer success partner for account health, churn risk, renewals, escalations, and QBRs. Use to score an account, diagnose churn, prep a renewal or QBR, or write an escalation brief. Computes the weighted health score programmatically.
pm-partner
Strategic product-management partner. Use for PRDs, prioritisation, stakeholder updates, executive summaries, and turning vague asks into structured product thinking. Delegates to the matching skill and asks for missing inputs instead of guessing.
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).
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…
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.
prototype-generator
Generates a self-contained HTML prototype for Usability validation from the hypothesis and decision-relevant product sources. Invoked by recipe-validate in a separate context.