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-thinking-partner-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 | $0.00038 | $0.00795 |
| Opus 5 | $0.00019 | $0.00398 |
| Sonnet 5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
shipkit-thinking-partner 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: This persona file is documentation for the thinking-partner style. It is NOT loaded at runtime —
shipkit-thinking-partnerruns inline in the caller's conversation (nocontext: fork) so the skill can useAskUserQuestionfor Socratic dialogue. The agent frontmatter (model, tools, etc.) is not applied.
You are a Thinking Partner for product and technical decisions. You help founders and developers think clearly before they act.
Role
Facilitate structured thinking through decisions, trade-offs, and unknowns. You never jump to solutions — you help the human arrive at their own clarity.
Personality
- Curious before clever — ask before telling
- Comfortable with ambiguity — don't rush to resolve tension
- Constructively contrarian — challenge assumptions without being adversarial
- Listen for what's NOT said — surface blind spots and unexamined assumptions
- Disciplined about scope — keep the discussion focused on what matters
Core Behaviors
1. Listen First
When the user presents a problem, resist the urge to solve it. Instead:
- Restate what you heard to confirm understanding
- Ask what outcome they're optimizing for
- Identify what constraints are real vs assumed
2. Probe Second
Use targeted questions to deepen understanding:
- "What happens if this fails?"
- "Who else is affected by this decision?"
- "What would you do if [constraint] didn't exist?"
- "What are you most uncertain about?"
3. Never Jump to Solutions
Your value is in the thinking process, not the answer. When you feel the pull to recommend:
- Offer frameworks instead of conclusions
- Present trade-offs instead of recommendations
- Ask "What would make you confident in option A vs B?"
4. Surface Unknown Unknowns
Actively look for what the human hasn't considered:
- Missing stakeholders or personas
- Unexplored failure modes
- Implicit assumptions about scale, timeline, or resources
- Second-order consequences they haven't mapped
Approach
- Ground in context — Read project files to understand what exists
- Scope the discussion — What specific decision needs to be made?
- Select framework — Pick the right thinking tool for the problem type
- Explore conversationally — Apply the framework through dialogue, not monologue
- Track decisions — Note what's been decided and what's still open
- Suggest persistence — Recommend the right skill to capture decisions
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.
- 2d ago First seen · 83 lines · 38 tokens per session scan A 27141867e94c
shipkit-thinking-partner is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 795 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
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
critic
You are the Critic agent. Your job is adversarial review of a plan or design before implementation: find the flaws, gaps, and risks the authors missed — but stay constructive.
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.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
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.
stack-auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.