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 LensmorOfficial/trade-show-skills --skill trade-show-competitor-radargit clone --depth 1 https://github.com/LensmorOfficial/trade-show-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/lensmorofficial/trade-show-skills/trade-show-competitor-radar)<a href="https://agentmods.dev/skills/lensmorofficial/trade-show-skills/trade-show-competitor-radar"><img src="https://agentmods.dev/badge/skills/lensmorofficial/trade-show-skills/trade-show-competitor-radar/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/lensmorofficial/trade-show-skills/trade-show-competitor-radar"><img src="https://agentmods.dev/badge/skills/lensmorofficial/trade-show-skills/trade-show-competitor-radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.01696 |
| Opus 5 | $0.00051 | $0.00848 |
| Sonnet 5 | $0.00020 | $0.00339 |
| Haiku 4.5 | $0.00010 | $0.00170 |
Grade A, and why
trade-show-competitor-radar 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 13d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Radar
Turn raw show-floor observations — typed notes, brochure text, overheard messaging, product announcement snippets — into structured competitive intelligence that your team can actually act on.
When this skill triggers:
- Use it during the show or right after booth visits while the observations are still fresh
- Use it for field-intel that needs explicit evidence tags before it reaches sales, product, or leadership
- Do not use it for pre-show public research; use
pre-show-competitor-analysisfor that
Workflow
Step 1: Structure Field Notes
Accept input in any form:
- Free-text observation notes ("Their booth was huge, new product launch, aggressive pricing signage")
- Brochure or collateral text (pasted or transcribed)
- Product announcement snippets (press release, in-show announcement, banner copy)
- Pricing clues (signage text, overhead conversations, quoted figures)
- Overheard conversations or show-floor gossip (label these clearly as unverified)
From the input, extract:
- Competitor name
- Show name / date (ask if not provided — context matters for the report)
- Source type for each data point: direct observation, printed material, overheard, or inferred
If the user provides observations about multiple competitors, process each separately then produce a cross-competitor summary.
Step 2: Separate Observation from Inference
This is the most important step. Every fact must be tagged:
| Tag | Meaning | Example |
|---|---|---|
| [OBS] | Directly observed or read verbatim | "Banner copy read: 'Now 40% faster'" |
| [INF] | Reasonably inferred from observable signals | "Heavy foot traffic suggests strong interest from [segment]" |
| [HEARD] | Overheard or reported second-hand — treat as unverified | "Sales rep told a visitor their price starts at €X" |
| [EST] | Estimated numerical value — not measured directly | "Booth footprint est. 200 sqm" |
| [UNK] | Cannot determine from available evidence |
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.
- 13d ago First seen · 139 lines · 102 tokens per session scan A db07256f81d8
trade-show-competitor-radar is a skill published in the GitHub repository LensmorOfficial/trade-show-skills (48 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,696 once invoked, about $0.0005 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
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
formula-authoring
Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.