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/stefanoskarakasis/Product-Marketing-SkillsWrote 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/commands/stefanoskarakasis/product-marketing-skills/competitive-briefing)<a href="https://agentmods.dev/commands/stefanoskarakasis/product-marketing-skills/competitive-briefing"><img src="https://agentmods.dev/badge/commands/stefanoskarakasis/product-marketing-skills/competitive-briefing/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/commands/stefanoskarakasis/product-marketing-skills/competitive-briefing"><img src="https://agentmods.dev/badge/commands/stefanoskarakasis/product-marketing-skills/competitive-briefing.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 | $0.00018 | $0.00483 |
| Opus 5.5 | $0.00007 | $0.00193 |
| Sonnet 5.5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
competitive-briefing 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 today.
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.
What it actually says
/pmm-competitive-intelligence:competitive-briefing -- Competitive Briefing
Builds the one-screen weekly brief for leadership: a verdict that names the
risk in euro, one recommended decision with options and what would change
the call, what moved ranked by exposure, the last call graded, and the next
call. Reads the profiles, cards, deep-dives, signals and outcome log you
already keep. Saves the record and two small ledgers (calls and decisions)
to /context/briefings/. Never writes the brain.
Invocation
/pmm-competitive-intelligence:competitive-briefing Weekly leadership brief for the CEO
/pmm-competitive-intelligence:competitive-briefing Board update on competitors, we have a pricing decision coming
/pmm-competitive-intelligence:competitive-briefing CRO brief, focus on win and loss
/pmm-competitive-intelligence:competitive-briefing Grade last week's call and show what is still open
Workflow
Uses the competitive-briefing skill. Loads the brain (or asks three quick
questions and holds the answers for the session), reads the newest profile
per roster competitor, the period's signals, the outcome log and the
earlier briefs, and checks the evidence floor: with no profile, signal or
paste, it builds nothing and says what is missing. It asks once about
audience, currency (euro by default), a verifier and where pipeline
figures come from. It checks your forbidden claims and prohibited items
and how each item was collected, builds the brief in a fixed order, runs a
14-check gate on its own work, saves the record, appends the call and
decision rows, and logs the session. The status stays HOLD until nothing
is held and you name who verified it.
A quiet week gets a short brief, not a skipped week. In a Slack thread it
posts a 150-word version; to run it every Monday, see
skills/competitive-briefing/references/brief-format.md, section 9.
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.
- today First seen · 41 lines · 18 tokens per session scan A 4491959d3d03
competitive-briefing is a command published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 483 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 2026-10-27.
Other commands, from other repositories
getpix
Find a free licensed image on the internet and add it to the project, optimized.
photo-pass
Art-direction photo pass over the site: add photography only where it earns its place.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
strategy
Create a comprehensive product strategy using the 9-section Strategy Canvas — from vision to defensibility.
privacy-policy
Draft a privacy policy covering data collection, usage, storage, and compliance requirements.
conjure
Use when you want to build a new Claude Code skill, agent, hook, or MCP server but aren't sure which — or when you want to describe what you want in plain language. Auto-detects the right artifact type, asks targeted questions, explains the reasoning, then builds it.