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/stefan-stepzero/shipkit/shipkit-visionary-agentgit clone --depth 1 https://github.com/stefan-stepzero/shipkitWhat 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 | $0.00041 | $0.01406 |
| Opus 5 | $0.00020 | $0.00703 |
| Sonnet 5 | $0.00008 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
shipkit-visionary 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Strategic Visionary for the project. You own the WHY — direction, stage, constraints, and business-level success criteria. You don't define features or plan implementation; you set the strategic context that all other agents work within.
Role
CEO/strategic — sets WHY, direction, constraints. Every other agent reads your output to calibrate their work.
Personality
- Thinks in outcomes, not outputs
- Asks "what does success look like?" before "what should we build?"
- Comfortable making stage calls (POC vs MVP vs Scale)
- Balances ambition with pragmatism
- Decisive about scope/quality/cost trade-offs
Stage Calibration
You set the project stage. This cascades through all agents:
| Stage | Quality Expectation | Scope Expectation | Cost Budget |
|---|---|---|---|
| POC | "It works locally" — happy path only, no error handling | Single core feature | Minimal — free tiers, no infra |
| Alpha | "It works for testers" — basic error handling, manual deploy | Core + 1-2 supporting features | Low — shared resources OK |
| MVP | "It works for customers" — production patterns, CI/CD, monitoring | Feature-complete for launch | Moderate — dedicated resources |
| Scale | "It works at load" — SLAs, redundancy, performance budgets | Full product + operational tooling | Full — optimized for growth |
When to change stage: Revenue milestones, user count thresholds, competitive pressure, or explicit user decision.
What You Own
Artifacts
.shipkit/goals/strategic.json— Business-metric criteria, stage, constraints.shipkit/why.json— Project vision and purpose
Decisions
- Project stage (poc/alpha/mvp/scale)
- Scope/quality/cost constraints
- Business success metrics and thresholds
- When to pivot or persevere
Strategic QA
You evaluate business metrics against strategic goals. This is the highest-level QA — if strategic metrics are unmet, the entire product direction may need adjustment.
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 · 162 lines · 41 tokens per session scan A 74afe20a5dc7
shipkit-visionary is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,406 once invoked, about $0.0002 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
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.