Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add heyparsadev/claude-venture-plugin/plugin install ventureWrote 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/heyparsadev/claude-venture-plugin/start)<a href="https://agentmods.dev/skills/heyparsadev/claude-venture-plugin/start"><img src="https://agentmods.dev/badge/skills/heyparsadev/claude-venture-plugin/start.svg" alt="Measured on agentmods" 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 | $0.00112 | $0.01441 |
| Opus 5 | $0.00056 | $0.00720 |
| Sonnet 5 | $0.00022 | $0.00288 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade C, and why
start 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 7d 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.
| با مشتریها حرف زدم، میخوام جدی بررسی کنم / validated interest | new-venture → deep market research + competitors | | دارم میسازم / building | new-venture → competitors + business model | | لانچ کردم ولی رشد کنده / l How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Biz Start — Dashboard, Router & Living Manual
The front door of the venture suite. Show where every venture stands, recommend the next move, and teach the suite interactively. Keep it conversational — short dashboard first, detail on demand. Never dump the full manual unprompted.
Shared conventions (venture suite)
- Workspace: locate
ventures/in the current working directory (ask once and create if missing). All outputs go toventures/<slug>/<NN-module>/. - Templates are read-only. Files under a skill's
references/live inside the installed plugin and are shared by every venture. Never write to them. "Fill template X" always means: copy it intoventures/<slug>/<NN-module>/under a dated name and fill the copy. - Read
VENTURE.mdfirst. When done: update its Status table and append key findings to "Key facts & numbers" (format:- [module, YYYY-MM-DD] finding (source, confidence)). - Language: converse in the user's language. Write formal deliverables (reports, canvases, battlecards) in the
report_languageset in VENTURE.md. Persian reports keep standard English business terms as-is (TAM, SAM, SOM, CAC, LTV, GTM, churn, retention...). - Research integrity: cite every external claim (source + date). Mark every estimate with confidence (high/med/low). Never fabricate numbers — write "no data found" instead.
- Chain: end by updating VENTURE.md and suggesting the logical next module.
Workflow
1. Scan
Read every ventures/*/VENTURE.md (only these files — not whole folders). No ventures/ directory or empty → skip to step 4 (first-time welcome).
2. Dashboard
Show a compact table in the user's language:
| Venture | Stage | Done | Stale/open | Suggested next step |
|---|
- "Done" = modules with
donestatus; "Stale" = stale modules or unchecked riskiest assumptions. - Flag ventures untouched for 30+ days.
- One venture only → skip the table, give a short narrative status instead.
3. Route
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.
- 7d ago First seen · 87 lines · 112 tokens per session scan C 2bc884ed6d71
start is a skill published in the GitHub repository heyparsadev/claude-venture-plugin (5 stars, last pushed 25d ago), licensed MIT. It adds 112 tokens to every session and 1,441 once invoked, about $0.0006 per session on Opus 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 skills, from other repositories
story-breakdown
Decompose a large problem, epic, or initiative into independently shippable slices. Use when work is too big to build in one sprint and you need to find the seams.
feature-sunset
Plan and communicate a feature or product end-of-life. Use when deprecating features, sunsetting products, or managing migration off legacy systems.
roadmap-planning
Translate strategy and OKRs into a sequenced product roadmap. Use when you need to communicate what's next, why, and in what order.
stakeholder-alignment
Align stakeholders on priorities, scope, or direction when there's disagreement. Use when you need buy-in fast, not just a status update.
tech-debt-communication
Quantify and communicate tech debt as a business decision. Use when engineering needs investment in infrastructure and you need to make the case to leadership.
epic-definition
Define an epic with strategic context, feature breakdown, milestones, and success metrics. Use when scoping a large body of work for planning and tracking.