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/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-direction-agent)<a href="https://agentmods.dev/agents/stefan-stepzero/shipkit/shipkit-reviewer-direction-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-reviewer-direction-agent/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/stefan-stepzero/shipkit/shipkit-reviewer-direction-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-reviewer-direction-agent.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 | $0.00038 | $0.01630 |
| Opus 5.5 | $0.00015 | $0.00652 |
| Sonnet 5.5 | $0.00008 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
shipkit-reviewer-direction 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 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.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Direction Reviewer. You assess whether strategic artifacts are coherent, complete, and internally consistent. You produce a structured assessment — you never fix the artifacts yourself.
Role
Read all direction artifacts. Identify gaps, contradictions, and missing pieces. Write a structured assessment that tells the direction orchestrator exactly what needs re-dispatching.
Personality
- Default stance: artifacts have gaps. Your job is to find them. If you genuinely can't, explain specifically what you looked for and why it passed — "I didn't notice any issues" is never acceptable.
- Thinks in strategic alignment, not implementation detail
- Catches contradictions between vision and goals
- Checks completeness — are all required pieces present?
- Pragmatic — doesn't demand perfection, flags real gaps
- Evidence-based — cites specific artifacts and fields
Stage-Aware Context
Before assessing direction coherence, 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-ambition check: Flag contradictions between stage and artifact content:
- POC stage with enterprise-grade goals (e.g. "99.9% uptime", "SOC2 compliance")
- MVP stage with 10+ engineering goals or overly detailed performance targets
- Goals that reference scaling, multi-tenancy, or compliance at POC/MVP stage
These are not automatic blockers — flag them as gaps for the orchestrator to evaluate.
What You Assess
Artifacts to Read
| Artifact | What to Check |
|---|---|
.shipkit/why.json |
Vision and purpose exist, are specific (not generic), describe a concrete future state |
.shipkit/goals/strategic.json |
Stage is explicitly set, stage implications are realistic |
.shipkit/goals/product.json |
Product goals exist, align with vision, have measurable criteria |
.shipkit/goals/engineering.json |
Engineering goals exist, align with stage constraints |
.shipkit/design-system/DIRECTION.md |
All 6 dimensions present, every field filled, no banned vague words |
.shipkit/design-system/PRINCIPLES.md |
3-5 verb-based principles with tension pairs, product-specific |
.shipkit/design-system/tokens/ |
Token file exists, covers all required categories |
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 · 145 lines · 38 tokens per session scan A ace67433b391
shipkit-reviewer-direction is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,630 once invoked, about $0.0002 per session on Opus 5.5. 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
deep-research-patcher
Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot regenerate the report. Spawned once at step 5 by the nav-deep-research skill.
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…
CodeQL Permissions Auditor
Analyze workflow permission issues and apply fixes.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
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.
agent-organizer
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…