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 skills/stefan-stepzero/shipkit/shipkit-adrnpx skills add stefan-stepzero/shipkit --skill shipkit-adrgit 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 | $0.00068 | $0.01638 |
| Opus 5 | $0.00034 | $0.00819 |
| Sonnet 5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
shipkit-adr 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-adr - Land a Decision Atomically
Purpose: Record one architecture decision the moment it's made — as a single atomic transaction across both decision files, with a hard length cap on what enters the always-loaded lean index.
Why this exists: architecture.json is @-imported into CLAUDE.md, so every byte of it loads into every session. The moment a decision gets recorded is exactly when a long rationale is freshest and most tempting to paste in. This skill enforces the lean/archive split at that moment: full reasoning is preserved (archive), context stays cheap (lean).
Output: One entry appended to .shipkit/architecture-archive.json (full) + the capped projection in .shipkit/architecture.json (lean).
When to Invoke
User triggers:
- "Record this decision" / "log an ADR"
- "We decided X" (after a decision is settled in conversation)
- "ADR-NNN is superseded by this" / "that replaces the earlier decision"
- "Amend ADR-NNN"
Agent triggers: Any skill or agent that has just made an architecture-level decision mid-work lands it here instead of hand-editing architecture.json.
Prerequisites
None. If either decision file is missing, this skill initializes it (schemas below). The canonical convention both files follow is shipkit-engineering-definition/references/architecture-log-schema.md — read it for edge cases; the operative rules are inlined here.
Hard Caps (non-negotiable)
What enters the lean file is capped. Full text always survives in the archive — leaning relocates information, it never loses it.
| Lean field | Cap |
|---|---|
decision |
one line, ≤ 120 chars |
rationale |
one line, ≤ 160 chars |
| superseded entry | stub only: { id, status, supersededBy, decision } — nothing else |
If the user's phrasing exceeds a cap, compress it for the lean file and put the full text in the archive entry. Never widen the cap; never put alternatives in the lean file.
Process
Step 1: Capture the decision
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 · 132 lines · 68 tokens per session scan A a894dc325976
shipkit-adr is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,638 once invoked, about $0.0003 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 skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.