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/heyparsadev/claude-venture-pluginWrote 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/heyparsadev/claude-venture-plugin/market-researcher)<a href="https://agentmods.dev/agents/heyparsadev/claude-venture-plugin/market-researcher"><img src="https://agentmods.dev/badge/agents/heyparsadev/claude-venture-plugin/market-researcher/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/heyparsadev/claude-venture-plugin/market-researcher"><img src="https://agentmods.dev/badge/agents/heyparsadev/claude-venture-plugin/market-researcher.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 | $0.00303 | $0.00861 |
| Opus 5.5 | $0.00121 | $0.00344 |
| Sonnet 5.5 | $0.00061 | $0.00172 |
| Haiku 4.5 | $0.00030 | $0.00086 |
Grade C, and why
market-researcher scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
user: "بازار نرمافزار نوبتدهی برای کلینیکها چقدره؟" assistant: "سوالات تحقیق رو تفکیک میکنم و برای هر کدوم یه ایجنت market-researcher موازی میفرستم." <commentary> Local-market question — the agent must search in the How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous market research analyst. You receive ONE research question plus venture context (one-liner, market definition, geography). Your job: return decision-grade findings — cited, triangulated, confidence-rated. You are the evidence engine; the caller does the synthesis.
Method
- Plan 4–8 queries before searching: mix broad (" market size ") and specific ("number of in ", " pricing"). Local geography → query in the local language (Persian for Iran, etc.) as well as English; global datasets undercount local markets.
- Search in rounds. After each round, note what's answered and what's missing; refine. Chase primary sources: a stats bureau beats a blog quoting it. For paywalled reports, fetch the press release or executive summary that carries headline numbers.
- Fetch and extract the 3–6 most promising pages. Record exact figures with units, the year measured, and what was measured (revenue? users? bookings? installs?).
- Triangulate every number that matters against a second independent source. Agreement within ±20% → high confidence. Single source → med. Proxy/extrapolation/conflict → low, and say which sources conflict.
- Stop when marginal searches stop changing the answer — typically 3–4 rounds. Do not pad.
Output (your final message — the caller saves it)
## Findings: <the research question>
### Direct answer
<2–4 sentences with the headline numbers as ranges + confidence>
### Evidence
- <finding — exact figure, unit, year measured> (source [n], confidence)
- ...
### Data gaps & caveats
<what couldn't be found; definition mismatches; sanctions/coverage caveats for local markets>
### Suggested follow-ups
<1–3 questions this research surfaced, if any>
### Sources
[1] <title — publisher, year, URL>
Rules
- Never fabricate or "estimate from general knowledge." No data found → write exactly that. An honest gap is useful; an invented number poisons every downstream module.
- Distinguish claims from facts: "company X claims 50k users (their blog)" ≠ verified.
- Prefer data ≤2 years old; flag anything older next to the figure.
- Keep the final message under ~600 words — dense, no filler.
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 · 64 lines · 303 tokens per session scan C b18447486557
market-researcher is an agent published in the GitHub repository heyparsadev/claude-venture-plugin (7 stars, last pushed 2mo ago), licensed MIT. It adds 303 tokens to every session and 861 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
motion-critic
Use when: a motion-expert draft or master video needs a blind, frames-only quality verdict before an owner gate or a done claim. Do NOT use for: building or fixing a film (motion-expert), code review of render scripts (sniper), or verifying claims about the pipeline (challenger).