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 getcrew44/crew44 --skill press-releasegit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/press-release)<a href="https://agentmods.dev/skills/getcrew44/crew44/press-release"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/press-release.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.02348 |
| Opus 5 | $0.00015 | $0.01174 |
| Sonnet 5 | $0.00006 | $0.00470 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
press-release 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 7d 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:
- press-release — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Create a visionary press release following Amazon's "Working Backwards" methodology to define and communicate a product or feature before building it. Use this to align stakeholders on the customer value proposition, clarify the problem being solved, and test if the product story resonates—treating the press release as a forcing function for clarity and customer-centricity.
This is not a marketing artifact for launch day—it's a planning tool that asks "If we shipped this perfectly, how would we explain it to the world?"
Key Concepts
The Amazon Working Backwards Framework
Popularized by Amazon, the Working Backwards process starts with a press release and FAQ before any code is written. The press release must:
- Be written from the customer's perspective
- Focus on the problem solved, not the features built
- Be short (1-1.5 pages)
- Be compelling enough that customers would want the product
Press Release Structure
A standard press release follows this format:
- Headline: Clear, benefit-focused product announcement
- Dateline: City, state, date
- Introduction paragraph: What's being launched, who it's for, key benefit
- Problem paragraph: Customer problem the product solves
- Solution paragraph: How the product addresses the problem (outcomes, not features)
- Quote from company leader: Vision, customer commitment
- Additional details: Supporting benefits or data
- Boilerplate: Company background
- Call to action: How to learn more
- Media contact: Press contact information
Why This Works
- Customer-first thinking: Forces you to articulate value from the customer's perspective
- Clarity forcing function: If you can't write a compelling press release, the product idea may be weak
- Alignment tool: Stakeholders can read and react to the vision before engineering starts
- Decision filter: If a feature wouldn't make it into the press release, question its priority
Anti-Patterns (What This Is NOT)
- Not feature-centric: Don't list specs—focus on customer outcomes
- Not internal jargon: Write for customers, not engineers
- Not vague: "Revolutionizes productivity" is fluff; "Reduces report generation time from 8 hours to 10 minutes" is real
- Not marketing spin: Be honest about what the product does
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 270 lines · 31 tokens per session scan A 8479c4028bd3
press-release is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,348 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 skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
mine-plan-create
Create or update an evidence-backed, architecture-governed software implementation plan that is precise enough for independent coding agents to execute without rediscovering design decisions. Scope-first: an explicit user scope defines the planning boundary; research-backed: substantive planning requires mandatory…