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.
npx skills add aleksander-dytko/ai-pm-workspace --skill competitive-researchgit clone --depth 1 https://github.com/aleksander-dytko/ai-pm-workspaceWrote 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/skills/aleksander-dytko/ai-pm-workspace/competitive-research)<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/competitive-research"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/competitive-research/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/skills/aleksander-dytko/ai-pm-workspace/competitive-research"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/competitive-research.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 | $0.00014 | $0.01147 |
| Opus 5.5 | $0.00006 | $0.00459 |
| Sonnet 5.5 | $0.00003 | $0.00229 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
competitive-research 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Research
You help produce a sourced competitive matrix for a focused research question. The output is a markdown table plus sourced observations, landed in research/.
Input
The user provides via $ARGUMENTS:
- A short research topic (e.g., "how competitors handle first-time user onboarding"), OR
- A path to a research-prompt file (e.g.,
samples/sample-competitor-prompt.md)
Workflow
1. Read the prompt
If $ARGUMENTS is a file path, read it. Otherwise use the prompt directly.
Extract (or ask in one round):
- Research topic - the question.
- Scope - which competitors (direct / adjacent / aspirational), any exclusions.
- Questions - 3-7 specific things you want answered.
- Deliverable format - matrix (rows = products, columns = questions) by default.
- Timeline and non-goals.
If any of these are missing, ask the user in ONE AskUserQuestion round. Skip any that are clear.
2. Pick the competitor set
If the user provided competitors, use them. Otherwise suggest a set and confirm:
- Direct: 2-3 products in the same pricing tier and feature surface as your own (list your company's known competitors from
CLAUDE.mdor ask). - Adjacent / aspirational: 1-2 products in related spaces known for excellent practice in the research topic.
- Exclude: tools clearly out of scope.
Confirm the list with the user before proceeding.
3. Gather observations (sourced)
For each product, for each research question, gather observations. Use available tools:
- WebFetch / WebSearch for public product docs, blog posts, marketing pages, changelog posts, and product-hunt-style coverage.
- Any documentation MCP your environment has configured (check the
MCP Servers Availablesection ofCLAUDE.md). - Internal research notes in
Loose Notes/Work/that mention the competitor by name.
Rules for observations:
- Sourced: every observation has a URL or an internal note reference. No "I think they probably...".
- Observed vs. inferred: mark each cell as
observed:(you can point to a specific page/screenshot) orinferred:(your reasoning based on other evidence). - Date-stamped: competitive landscapes move fast. Note the date of the source when it's older than 6 months.
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 · 116 lines · 14 tokens per session scan A afe39af5c292
competitive-research is a skill published in the GitHub repository aleksander-dytko/ai-pm-workspace (34 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,147 once invoked, about $0.0001 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 skills, from other repositories
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
morning-intelligence
Interviews you across 15 questions to capture your role, topics, sources, exclusions, and format preferences, then writes a master prompt you can paste into a scheduled task or Claude Code Routine. Use when you want to set up a personalised daily news brief, build a reusable morning news prompt, or create an automated…
technical-spec-template
Crea documentos de especificación técnica estructurados que conectan requisitos de producto con implementación de ingeniería. Úsalo cuando escribas una especificación técnica, especificación de ingeniería, documento de diseño de sistema o especificación de API. Produce una especificación completa con declaración del…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…
explorer-pipeline
Use when asked to make an interactive 3D explorer of a topic from start to finish, go from a topic to a clickable 3D learning page, or run the whole 3D explorer process. Produces a staged run of explorer-interface-brief, model-prompt-pack and explorer-viewer-builder in order for one topic, with the hand-offs between…