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 lossless-group/lossless-agent-skills --skill competitive-analysisgit clone --depth 1 https://github.com/lossless-group/lossless-agent-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/lossless-group/lossless-agent-skills/competitive-analysis)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/competitive-analysis"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/competitive-analysis/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/lossless-group/lossless-agent-skills/competitive-analysis"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/competitive-analysis.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 | $0.00182 | $0.02215 |
| Opus 5 | $0.00091 | $0.01107 |
| Sonnet 5 | $0.00036 | $0.00443 |
| Haiku 4.5 | $0.00018 | $0.00221 |
Grade A, and why
competitive-analysis 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 10d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Analysis Taxonomy
Competitive analysis for an investment memo is built on two orthogonal axes:
- Stage ring — concentric circles outward from the target company's own stage of development. The target sits at the center; competitors are placed on the ring that matches their stage, not the target's.
- Competitor type — how structurally similar the competitor's offering, value proposition, and customer set are to the target's.
Every competitor named in a memo should be tagged on both axes.
Axis 1 — Stage Rings
The target company sits at the center. Competitors are sorted onto rings by their own funding stage / scale, not the target's. A seed-stage target with incumbents on its outer ring tells a very different story than a seed-stage target whose entire landscape is other seed-stage companies.
| Ring | Definition |
|---|---|
early stage |
Pre-Seed, Seed, Series A |
early scaleup |
Series B, Series C |
scaleup |
Series D and beyond, prior to mezzanine |
mezzanine |
Pre-IPO rounds where valuation exceeds ~$2–3B |
incumbents |
Public companies, or massive PE-owned rollups |
How to use the rings
- Place the target on its own ring first. Everything else gets classified relative to that center, but each competitor is named on the ring matching its own stage.
- A complete competitive picture spans multiple rings outward — being only compared against same-ring peers usually hides the real threat (
noisewashingincumbents, or scaleups about to enter the segment). - A target with no
early stagecompetitors but manyincumbentsis in a different position than one surrounded by same-ring peers — both facts belong in the memo.
Axis 2 — Competitor Types
These four types describe the structural relationship between a competitor and the target. They are listed roughly inside-out by directness of threat.
direct
Offers essentially the same set of services/products, has essentially the same value proposition, and sells to essentially the same customer set.
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.
- 10d ago First seen · 126 lines · 182 tokens per session scan A 2e185aa013f0
competitive-analysis is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 17d ago), licensed MIT. It adds 182 tokens to every session and 2,215 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
session-review
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
second-opinion
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…
close-session
An end-of-session workflow that reviews new lessons, asks before promoting repeated patterns, refreshes memory files, and writes a handoff.
ios26-api-reference
Authoritative iOS/macOS/watchOS 26 API reference with 3-tier smart loading. Prevents crashes from hallucinated APIs. Trigger on ANY code involving FoundationModels, SpeechTranscriber, SpeechAnalyzer, @Generable, LanguageModelSession, glassEffect, SwiftData, @Observable, Live Activity, App Intents, Vision…
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…