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 SupercmoHQ/superCMO-skills --skill identifying-competitorsgit clone --depth 1 https://github.com/SupercmoHQ/superCMO-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/skills/supercmohq/supercmo-skills/identifying-competitors)<a href="https://agentmods.dev/skills/supercmohq/supercmo-skills/identifying-competitors"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/identifying-competitors/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/supercmohq/supercmo-skills/identifying-competitors"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/identifying-competitors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 46 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00074 | $0.00983 |
| Opus 5.5 | $0.00030 | $0.00393 |
| Sonnet 5.5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
identifying-competitors 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitors
Find who a brand competes with, confirm the list, and hand it over. Names and websites only.
Workflow
Step 1: Check whether the competitors are already known
Read competitors.md in ./supercmo-company, and brand.md for the brand's name, website and what it sells. Where competitors.md already holds this brand's competitors, hand them back and stop — re-searching bills again and tells the user nothing new. Carry on where it's missing, where it's a different brand, or where the user asked to refresh.
Step 2: Settle the brand
You need a brand name and a website. Where you don't already have them, ask the user for whichever is missing. Do not proceed without the website.
Step 3: Learn what the brand sells
Call url_extraction on the website to learn what the brand sells. Skip this where you already know.
Step 4: Find the candidates
Search the web with queries like:
alternatives to <brand>— how buyers who already know the brand shop around.best <category> for <audience>— how buyers who don't yet know the brand find the category.
The search comes back with an answer and the source it drew from. Take the competitor names from there, and each website from a result or an ad's landing_url that links to the competitor's own site — not
a store, marketplace or social page. Where a result names a competitor without its site, search its
name for its official site. Where nothing shows one, write "website unconfirmed" — never a
domain from memory. Where a query returns nothing, vary the category words and search again.
Every candidate needs a source — the search result that named it. Don't add competitors from memory.
Where search runs thin — a niche category, a non-English market — social_research on meta_ad_library / search_ads with the category words shows who actually advertises in the space. Pass country for the market the brand sells in, where its page or brand.md shows it; where
nothing does, leave it out. It spends credits: say so and wait for a yes. Under a brief that skips
confirmation, run it without asking.
What ships with it
1 file 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.
- 12d ago Changed · +8 lines c9769aa144ac
- 1mo ago First seen · 64 lines · 74 tokens per session scan A 0364154808b6
identifying-competitors is a skill published in the GitHub repository SupercmoHQ/superCMO-skills (242 stars, last pushed 6d ago), licensed Apache-2.0. It adds 74 tokens to every session and 983 once invoked, about $0.0003 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
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).