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 | $0.00049 | $0.01939 |
| Opus 5.5 | $0.00020 | $0.00776 |
| Sonnet 5.5 | $0.00010 | $0.00388 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
competitive-researcher 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Fetch submissions.** `GET https://data.sec.gov/submissions/CIK##########.json`. Send a declared `User-Agent` that names this plugin and a contact the PM agrees to, for example `PM Superpowers moat-research (contact: Copies of this mod
1 near-identical copy found in the catalogue:
- competitive-researcher — 100% identical, 39 lines differ
How it starts
The opening of the file, as written. The whole thing — 133 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
SEC filing fetch
Run this only when find-your-moat or strategic-moat turns on public-company mode. Do not run it for a private or early-stage product. Do not run it during an ordinary competitive-landscape pass unless that pass also asked for a filing.
US filers: latest 10-K. Non-US filers: latest 20-F, or the company's annual report when it has no SEC filing. Return a filing extract. Do not paste the whole document into the moat write-up.
- Resolve the ticker. Load
https://www.sec.gov/files/company_tickers.json. Match the ticker (case-insensitive) and readcik_strandtitle. The submissions CIK iscik_strzero-padded to 10 digits. - Fetch submissions.
GET https://data.sec.gov/submissions/CIK##########.json. Send a declaredUser-Agentthat names this plugin and a contact the PM agrees to, for examplePM Superpowers moat-research (contact: [email protected]). If they do not provide a contact, usePM Superpowers moat-research (contact: [email protected])and say the contact is a placeholder. SEC rejects requests with no User-Agent. Send it via WebFetch when that tool allows headers; otherwisecurl -A "<User-Agent>". On 403 or 429, wait and retry once. Do not hammer. - Pick the filing. In
filings.recent, take the first row whoseformis10-K(US) or20-F(foreign private issuer). Recordform,filingDate,accessionNumber, andprimaryDocument. Also record the issuercikfrom the top of the JSON. - Open the primary document.
https://www.sec.gov/Archives/edgar/data/{cik_unpadded}/{accession_without_dashes}/{primaryDocument}. The path CIK is the issuer CIK, not the accession prefix (a filing agent can make those differ). Same User-Agent as step 2. - Extract, do not summarize away the names. From Item 1, the Competition subsection: every company named and every competitor category the filing stresses. From Item 1A: the risk-factor headings, plus a short clause where a heading bears on the moat. Note form, filing date, and accession number.
- No CIK. If the ticker is not in
company_tickers.json, look for a 20-F filer. If there is still no CIK, fetch the latest annual report from the investor-relations site and cite the competition section and the risk headings. Say it is an annual report, not a 10-K. - Failure. If the fetch fails, return
Fetch status: failedand the reason. Do not invent quotes, accession numbers, or figures. The moat skill will continue on user and public-web evidence.
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 Changed · +35 lines · +12 tokens per session e5032f6eba05
- 1mo 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 (49 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,939 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
evaluator
Use when running one side of an A/B skill evaluation or chain verification. Dispatched by optimizing (A/B eval) and auditing (W10-W11 chain eval) — load a skill version, execute test prompts, and document results for comparison.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.