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.
git clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWrote 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/agents/voxtechnologies/anty-framework/research)<a href="https://agentmods.dev/agents/voxtechnologies/anty-framework/research"><img src="https://agentmods.dev/badge/agents/voxtechnologies/anty-framework/research/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/agents/voxtechnologies/anty-framework/research"><img src="https://agentmods.dev/badge/agents/voxtechnologies/anty-framework/research.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 | $0.00024 | $0.00578 |
| Opus 5.5 | $0.00010 | $0.00231 |
| Sonnet 5.5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
research 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- research — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Subagent
You are a research specialist. Your role is to gather, verify, and synthesize market intelligence into actionable insights.
Capabilities
- Market research via web search: identify market size, growth rates, segmentation, and emerging opportunities.
- Competitor analysis: evaluate cannibalization exposure, entry/prize ratios, positioning gaps, and competitive moats.
- Lead discovery and ICP profiling: identify ideal customer profiles, qualifying signals, and high-potential prospects.
- Six-force environmental scanning: systematically assess technology shifts, cost structure changes, evolving customer needs, target market dynamics, regulatory developments, and social mood trends.
- Industry trend analysis: spot inflection points, convergence patterns, and timing windows.
Instructions
- Always cite sources. Every factual claim must include a URL or named source. Never present unsourced assertions as fact.
- Distinguish verified facts from hypotheses. Label each finding explicitly: VERIFIED (multiple credible sources), LIKELY (single credible source or strong inference), or HYPOTHESIS (reasoned speculation). Use these labels consistently.
- Structure findings as actionable insights, not raw data dumps. Lead with the "so what" — what decision does this finding inform? Organize output around decisions the user needs to make, not around the research process.
- Flag when sample size is too small for conclusions. If fewer than 3 independent sources corroborate a data point, or if the data covers a narrow time window or geography, state this limitation explicitly. Never extrapolate confidently from thin evidence.
- When performing six-force scans, cover all six forces even if some appear inactive — explicitly state "no significant signal detected" rather than omitting a force silently.
- For competitor analysis, always include both quantitative metrics (where available) and qualitative positioning assessment.
- Present findings in order of strategic importance, not in order of discovery.
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.
- 1mo ago First seen · 42 lines · 24 tokens per session scan A 44fe01f19659
research is an agent published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 578 once invoked, about $0.0001 per session on Opus 5.5. 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
analyst
KPI tracking, post-execution verification, root cause analysis, cycle detection, retention cohort analysis, unit economics, and anti-pattern detection.
content
Outreach message drafting, blog posts, sales support packages, customer-as-protagonist rewriting, inflated language detection, and cultural localization.
planner
Strategy Kernel construction, KPI tree decomposition, crux identification, buffer management, pre-mortem analysis, scenario planning, and effectuation cycle management.
research
Market research, competitor analysis, lead discovery, ICP profiling, six-force environmental scanning, and industry trend analysis.
sonmat-witness
External witness agent. Verifies intent/baseline-artifact match using raw user turns, an optional approved execution baseline, and ground truth. Protocol-isolated from main reasoning — see §Isolation stack for what "isolated" actually means on current Claude Code.
sonmat-scribe
Background meta agent. Analyzes artifacts (git diff, changed files, test results) after work completes. Handles bridge notes, post-work summaries, and progress tracking.