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/mo-root/open-kb/linkgit clone --depth 1 https://github.com/mo-root/open-kbWhat 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 | $0.00000 | $0.00441 |
| Opus 5 | $0.00000 | $0.00220 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
link 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 yesterday.
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
Say how these pairs of companies relate to EACH OTHER.
The map is being built around {{anchor}} — {{sells}} — but that anchor is not the subject here. Every edge you write joins two of the pairs below, and the anchor is not one of them. A map where everything connects only to the company at the centre is a list with a middle, not a market.
Each pair below was returned by the same search two or more times. That is the only reason they are in front of you: a search engine putting two hosts on one results page is the engine saying they answer the same question. It is a strong hint and it is not a verdict. Plenty of pairs co-occur because a listicle named both.
For each pair, either write one edge or write nothing.
fromandtoare the domains exactly as given. Direction carries meaning and is not reversible: a publishercoversa vendor, a directorylistsone, a communitydiscussesone. Never the other way round.competitormeans these two would appear on the same shortlist.substitutemeans one removes the need for the other by a different route.confidenceismeasuredonly when a page you were shown put these two together for a stated reason. Otherwise it isinferred. Do not mark something measured because it feels certain.whysays HOW they relate, in a line a reader can act on or correct. "Both in web scraping" is worth nothing.whySpanis one quote, copied character-for-character from either company's description above, that backswhyspecifically. Leave it out rather than paraphrase or invent one.
Write nothing at all for a pair that merely appeared together. Two vendors listed in the same roundup are not automatically rivals, a blog and a forum that both mention a topic have no relation to each other, and an edge nobody can defend is worse than a gap.
{{pairs}}
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.
- yesterday First seen · 35 lines · 0 tokens per session scan A 10c03debcfeb
link is an agent published in the GitHub repository mo-root/open-kb (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 441 tokens. 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 agents, from other repositories
research-orchestrator
Orchestrator agent for sigint research sessions. Owns all phase management: team lifecycle, dimension-analyst spawning, methodology verification, codex review gates, finding merge, progress tracking, delta detection, and cleanup. Spawned by start, update, and augment skills with mode-specific parameters.
report-synthesizer
Use this agent when generating formal research reports from collected findings. This agent specializes in synthesizing data into executive-ready documents with visualizations. Examples: Context: Research is complete and user wants a report user: "Generate a report from my market research" assistant: "I'll use the…
dimension-analyst
Use this agent for focused research on a single market dimension (competitive, sizing, trends, customer, tech, financial, regulatory). Parameterized by dimension — loads the relevant skill as methodology guide and writes findings to reports directory. Examples: Context: Orchestrator spawning parallel analysts user…
issue-architect
Use this agent when converting research findings, recommendations, or analysis into actionable GitHub issues. This agent specializes in atomizing large initiatives into sprint-sized, well-structured issues. Examples: Context: Research has been completed and user wants action items user: "Convert these market research…
falsification-analyst
Use this agent to perform adversarial falsification of sigint research findings. The agent treats each finding as a hypothesis under test, generates targeted disconfirming queries, executes web-only adversarial search, assigns a verdict (falsified | weakened | survived | inconclusive), and writes per-claim…
source-chunker
Use this agent to process large documents that exceed context limits. Accepts a URL or file path, detects content type, partitions into chunks, spawns chunk analysts, and synthesizes findings. Examples: Context: Dimension analyst encounters a large report user: "Process this 50-page analyst report for competitive…