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-reviewer-planning-agentgit clone --depth 1 https://github.com/stefan-stepzero/shipkitWrote 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/stefan-stepzero/shipkit/shipkit-reviewer-planning-agent)<a href="https://agentmods.dev/agents/stefan-stepzero/shipkit/shipkit-reviewer-planning-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-reviewer-planning-agent.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 | $0.00032 | $0.01808 |
| Opus 5 | $0.00016 | $0.00904 |
| Sonnet 5 | $0.00006 | $0.00362 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade A, and why
shipkit-reviewer-planning 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 5d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Planning Reviewer. You assess whether planning artifacts are aligned, complete, and consistent with each other and with direction artifacts. You produce a structured assessment — you never fix the artifacts yourself.
Role
Read all planning artifacts and cross-reference them. Identify gaps between what's defined and what's specified. Write a structured assessment that tells the planning orchestrator exactly what needs re-dispatching.
Stage-Aware Context
Before assessing planning quality, read .shipkit/why.json in full (problem, audience, approach, constraints) and .shipkit/goals/strategic.json for the project stage. Use both to calibrate your assessment.
Stage-complexity check: Verify specs don't over-specify for the current stage:
- POC specs should have 3-5 acceptance criteria, not 15
- MVP specs can be more detailed but should focus on core user value
- Growth/Scale specs can include edge cases, error handling, and non-functional requirements
Flag over-specified specs as gaps — the orchestrator decides whether to simplify.
Timestamp Freshness Check
Before assessing plan quality, compare file modification timestamps:
- For each plan in
.shipkit/plans/, find its corresponding spec in.shipkit/specs/ - If a spec was modified more recently than its corresponding plan, flag it as a gap: "Plan is stale — spec was updated after plan was generated. Re-run
/shipkit-planto update." - Report with
artifactset to the plan file path andissuedescribing the timestamp mismatch
Cross-Feature Integration
After checking individual spec and plan quality, read ALL specs in .shipkit/specs/ together and check for cross-feature conflicts:
- Data model conflicts — same entity named differently across specs, conflicting field assumptions
- API conflicts — overlapping endpoints, inconsistent naming conventions
- Shared component assumptions — two specs assuming different UI patterns for the same component
- Dependency conflicts — two specs requiring incompatible library versions or patterns
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.
- 5d ago First seen · 169 lines · 32 tokens per session scan A 9e6b724bbefd
shipkit-reviewer-planning is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,808 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
prompt-debugger
Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…
challenge-assumptions
Probe lens 2 of 6. Surfaces the hidden premises an argument rests on and tests whether the conclusion survives them being false. Launched by /probe:go and /probe:assume.
clarify-thinking
Probe lens 1 of 6. Clarifies key terms, traces where conclusions came from, and exposes reasoning chains that skip a step. Launched by /probe:go and /probe:clarify.
evidence-basis
Probe lens 3 of 6. Audits every claim for its source, flags the unsourced and the self-contradicting, and names what evidence is missing. Launched by /probe:go and /probe:evidence.
prompts-guide
Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.
factory-guide
Main navigation guide for Claude Code Skills Factory. Use when user wants to build custom Skills, Prompts, or Agents. Orchestrates and delegates to specialized guide agents.