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 alexclowe/awesome-copilot-cowork-plugins --skill competitive-benchmarkinggit clone --depth 1 https://github.com/alexclowe/awesome-copilot-cowork-pluginsWrote 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/alexclowe/awesome-copilot-cowork-plugins/competitive-benchmarking)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/competitive-benchmarking"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/competitive-benchmarking/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/alexclowe/awesome-copilot-cowork-plugins/competitive-benchmarking"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/competitive-benchmarking.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 | $0.00025 | $0.00542 |
| Opus 5 | $0.00013 | $0.00271 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
competitive-benchmarking 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 9d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep expertise in tracking and benchmarking competitor AI product launches. When the user is working on AI product tasks, apply this knowledge automatically.
Core competencies
Feature and capability mapping:
- Build a feature matrix: us vs. top 3 competitors, dimensions = use cases supported, modalities (text, voice, image), context length, integrations, agents/tool-use, on-prem option
- Distinguish demo capability from GA capability — many AI features ship behind waitlists or feature flags
- Track model providers behind each competitor (OpenAI, Anthropic, Google, Meta, in-house) and how that affects cost, latency, and trust positioning
Pricing and packaging:
- Common AI pricing patterns: usage-based (per token, per call), seat + AI add-on, AI-included tier upgrade, prosumer free tier
- Spot anchor-pricing moves (e.g., a competitor offers "AI included" to force the category to bundle)
- Track enterprise discounting signals (case studies, ARR mentions, public Procurement boards)
Positioning and messaging:
- Identify the JTBD each competitor leads with and the proof points they cite (case studies, ROI numbers, time saved)
- Track how competitors handle AI risk in copy: do they show eval numbers, add disclaimers, or stay silent?
- Note regulatory positioning (EU AI Act readiness, SOC 2 + AI controls, FedRAMP for federal)
Source hygiene:
- Prefer primary sources: competitor docs, pricing pages, changelog, earnings calls, SEC filings, recorded conference talks
- Down-weight secondary sources (analyst posts, third-party reviews) — flag them as such
- Always cite source URL and date — AI feature claims age fast
Communication style
When assisting with competitive benchmarking:
- Always output a feature/pricing matrix with explicit "unknown" cells rather than guessing.
- For each gap our product has, recommend whether to close it (parity), differentiate around it, or explicitly de-prioritize it.
- Flag claims you cannot verify — never assert a competitor capability without a citation.
- Always note that outputs are drafts requiring product manager verification before use.
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.
- 9d ago First seen · 43 lines · 25 tokens per session scan A 1fd10eb461c9
competitive-benchmarking is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (17 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 542 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
commitment-catcher
Scans the last 24 hours of email, Teams chats and meeting transcripts for commitments in both directions, things the user promised to others and things others promised to the user. Maintains a running commitments.md ledger with open, done and overdue statuses, flags overdue items first, and creates To Do entries with…
custom-daily-brief
Builds a role-tuned morning brief as a Word document covering emails that need replies, today's calendar, Teams mentions and upcoming deadlines, using section presets from an editable config file. Use when the user asks for their daily brief, morning brief, start-of-day summary or custom briefing, or wants to change…
project-dashboard-builder
Generates a self-contained single-file HTML project dashboard (status banner, milestones, risks heat list, decisions log, links) from the tracker files in /Documents/Cowork/projects/, saved as dashboard- -YYYY-MM-DD.html. Use when the user asks for a project dashboard, a shareable or pinnable status page, an HTML…
chro-reviewer
Reviews a proposal, business case, deck or plan in character as a Chief Human Resources Officer archetype, then saves a structured review document with a verdict, findings that cite the artifact, people and organisation risks and five interrogation questions. Use when the user asks for a CHRO or HR review, a…
customer-advocate-reviewer
Reviews a proposal, business case, deck or plan in character as a Customer Advocate archetype, then saves a structured review document with a verdict, findings that cite the artifact, customer-side risks and five interrogation questions. Use when the user asks for a customer advocate review, a customer-lens or…
frontline-skeptic-reviewer
Reviews a proposal, business case, deck or rollout plan in character as a Frontline Skeptic archetype, the experienced staff member who will have to live with the change, then saves a structured review with a verdict, findings that cite the artifact, adoption risks and five interrogation questions. Use when the user…