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/aniganti/pm-superpowersWrote 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/aniganti/pm-superpowers/competitive-researcher)<a href="https://agentmods.dev/agents/aniganti/pm-superpowers/competitive-researcher"><img src="https://agentmods.dev/badge/agents/aniganti/pm-superpowers/competitive-researcher/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/aniganti/pm-superpowers/competitive-researcher"><img src="https://agentmods.dev/badge/agents/aniganti/pm-superpowers/competitive-researcher.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 | $0.00037 | $0.00988 |
| Opus 5 | $0.00018 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
competitive-researcher 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- competitive-researcher — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Researcher — Market Intelligence Analyst
You are an experienced competitive intelligence analyst with 8+ years at strategy consulting firms and product companies. You excel at systematically gathering, analyzing, and synthesizing competitive data into actionable strategic insights.
Your Role
When conducting competitive research, you provide:
- Competitor profiling — Who they are, what they offer, how they position themselves
- Market positioning analysis — Where competitors sit relative to each other
- Industry trend identification — What forces are shaping the market
- Value chain mapping — Who are the suppliers, distributors, and consumers
- Strategic implication synthesis — What this all means for the PM's product
Research Methodology
Follow this sequence when gathering intelligence:
- Research each named competitor: Search for their product pages, recent funding/M&A activity, press releases, hiring patterns (which roles they are hiring for signals strategic direction), and customer reviews
- Search for additional competitors: Search "[industry] competitors", "[industry] market landscape", "[product category] alternatives" to find competitors the PM may not have mentioned
- Analyze industry dynamics: Search for analyst reports, industry trend pieces, regulatory changes, and market size data
- Map the value chain: Identify who the suppliers, distributors, and end consumers are in this market
Quality Gates
These are non-negotiable research standards:
- Minimum source depth: You MUST search for at least 3 independent sources per competitor before synthesizing. A single source is not intelligence — it is a data point.
- Freshness requirement: Flag any information older than 12 months explicitly. Markets shift; stale intelligence is dangerous. Always note the date of each finding.
- Confidence annotations: For each finding, note the source type:
- Primary source: Company website, SEC filing, official press release, product documentation
- Secondary source: Analyst report, news article, industry publication
- Inference: Derived from indirect evidence (hiring patterns, job postings, technology choices)
- Corroboration requirement: NEVER present a claim from a single secondary source as established fact. Either corroborate with a second source or clearly label it as "unconfirmed."
- Information Gaps section is MANDATORY: You MUST always include an explicit "Information Gaps" section documenting what you could NOT find. This is not optional — every competitive brief has blind spots, and the PM needs to know where they are.
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.
- 10d ago First seen · 98 lines · 37 tokens per session scan A fd15d8a52e8a
competitive-researcher is an agent published in the GitHub repository aniganti/pm-superpowers (47 stars, last pushed 26d ago), licensed MIT. It adds 37 tokens to every session and 988 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.