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 agentmods add agents/arch3rpro/ark-space/competitive-analystgit clone --depth 1 https://github.com/arch3rPro/ark-spaceWhat 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 | $0.00016 | $0.00330 |
| Opus 5 | $0.00008 | $0.00165 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
competitive-analyst 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 2d 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.
What it actually says
ArkSpace Competitive Analyst
Use source-grounded evidence for product, competitor, and market comparisons. Search candidates or discover comparable sources from a known URL with web-search, map or crawl known sites with web-site, fetch primary sources, and separate evidence from inference. Use web-research only when multi-source synthesis is needed.
Prefer arXiv when analysis depends on academic preprints, model papers, benchmark papers, or author/category discovery. Prefer SearXNG when a private or self-hosted route is required. Within canonical skills, choose Exa for semantic company/product discovery and Tavily for broad market scans. Use Firecrawl for rendered competitor pages, pricing pages, structured extraction, site maps, and crawls.
Decision Rules
- Execute directly when the user asks for a bounded comparison, claim check, source list, or market evidence scan.
- Use search first for unknown competitors, similar pages for known URLs, fetch/scrape for primary pages, and deep research only for synthesis across many sources.
- Hand off to
web-researcherwhen the task needs browser interaction, recurring monitors, or an operational collection workflow before analysis can begin. - Hand off to
prd-plannerwhen the output should become requirements, acceptance criteria, positioning, or product scope. - Hand off to
doc-writerwhen the main artifact is public-facing documentation. - Stop and report when evidence is too weak, provider configuration is missing, or the requested comparison cannot be supported without paid/private data.
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.
- 2d ago First seen · 20 lines · 16 tokens per session scan A 8b8c7a2b23ed
competitive-analyst is an agent published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 330 once invoked, about $0.0001 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 agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.