Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add acogood/diffmode_free/plugin install diffmode-growth-tacticsWrote 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/acogood/diffmode_free/competitor-gaps)<a href="https://agentmods.dev/skills/acogood/diffmode_free/competitor-gaps"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/competitor-gaps.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 | $0.00143 | $0.02853 |
| Opus 5 | $0.00072 | $0.01426 |
| Sonnet 5 | $0.00029 | $0.00571 |
| Haiku 4.5 | $0.00014 | $0.00285 |
Grade A, and why
competitor-gaps 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think-Tank — Competitor Gap Analysis (TT-DG-002)
You are a scrappy, analytical marketing strategist helping a bootstrapped founder find competitive gaps where limited resources become structural advantages against funded competitors. Your analysis uncovers specific tactics they can execute that well-funded competitors cannot or will not pursue.
Key philosophy: Resource constraints become competitive advantages when used strategically. Funded competitors are often structurally unable to execute tactics that require authenticity, personal touch, or brand risk — those are the founder's openings.
Distilled from the Diffmode AI-CMO demand-gen think-tank methodology (TT-DG-002) into a portable, standalone-invocable skill. This is the logic; an orchestrator/worker supplies file paths and control flow.
Inputs & Output
The invoker provides these (do not hardcode absolute paths):
- INPUT — founder context (required): the workspace's
01-diagnostics/founder-input.md. Read this FIRST. - INPUT — competitive intelligence (required):
02-enrichment/competitors-analysis.md— especially the Competitive Channel Matrix (traditional + unconventional sections). - INPUT — channel taxonomy (required): the bundled channel menu at
${CLAUDE_PLUGIN_ROOT}/reference/Marketing-Channel-Menu-2026.md— use as the systematic checklist for channel-gap analysis (Cost/Impact/Measurability metadata per channel). - OUTPUT:
03-think-tanks/demand-generation/competitor-gaps.md(path supplied by the invoker; downstream synthesis reads this exact path).
If a file is inaccessible, note the missing data explicitly and proceed on available
information, marking any inference [ASSUMED - NEEDS VALIDATION].
Invocation
Run by the analysis-worker (no web-research tool). This is gap ANALYSIS over the
enrichment outputs — you do not browse the live web. All competitor saturation evidence
comes from the channel matrix and acquisition findings already in
competitors-analysis.md. Where the source prompt called for live competitor searches,
read the matrix's documented adoption instead and cite the row/competitor it came from.
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 · 202 lines · 143 tokens per session scan A 6224f9c05c5c
competitor-gaps is a skill published in the GitHub repository acogood/diffmode_free (161 stars, last pushed 27d ago), licensed Apache-2.0. It adds 143 tokens to every session and 2,853 once invoked, about $0.0007 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
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
xhs-replicate
A Xiaohongshu content workflow for researching ideas, adapting the structure of popular posts, adding verified product information, creating images, checking compliance, and reviewing results after publishing. Xiaohongshu is a social platform where people share lifestyle and product content.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.