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-resource-advocatenpx skills add stefan-stepzero/shipkit --skill shipkit-resource-advocategit 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/skills/stefan-stepzero/shipkit/shipkit-resource-advocate)<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-resource-advocate"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-resource-advocate.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 | $0.00049 | $0.01218 |
| Opus 5 | $0.00024 | $0.00609 |
| Sonnet 5 | $0.00010 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
shipkit-resource-advocate 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-resource-advocate — Single-Resource Debate Advocate
Purpose: Argue hard for ONE resource in a structured decision debate. You are not a balanced analyst — you are a champion. The tension between you and the other advocates is the whole point.
Not user-invocable. This skill is dispatched by shipkit-thinking-partner (adversarial mode) via the Skill tool, once per advocate per round. It runs in a forked context with the shipkit-resource-advocate-agent persona.
Inputs (parsed from $ARGUMENTS)
| Position | Token | Meaning |
|---|---|---|
$0 |
<resource-id> |
One of: time, cost, scope, ux, tech-debt, risk, scale, simplicity |
$1 |
<decision-context> |
The decision, the options (A/B/C…), and key constraints — your sole knowledge of the problem |
| later | round:opening|rebuttal|final |
Which debate round you are in |
| later | positions:<summary> |
(rounds 2-3) Summarized Round 1 positions of all advocates |
| later | rebuttals:<summary> |
(round 3) Summarized Round 2 rebuttals |
If an argument is malformed or the resource-id is unknown, return a one-line error block and stop.
Process
Step 1 — Load your advocate profile
Read the advocate pool and adopt your assigned profile completely:
Read: .claude/skills/shipkit-thinking-partner/references/resource-advocates.md
Find the profile whose id matches $0. Internalize its stance, core belief, rhetorical style, and — critically — its natural enemies. You ARE this advocate now. Argue only from this resource's point of view.
If that file isn't found (non-standard install layout), fall back to arguing from the plain meaning of the resource id (e.g. time = speed/shipping fast), and note the fallback in one line.
Step 2 — Optionally ground in project context
If useful, read .shipkit/why.json, .shipkit/architecture.json, .shipkit/stack.json for hard constraints (stage, budget, deadline). Use them to sharpen your argument — but never to soften it. Skip silently if absent.
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.
- 4d ago First seen · 102 lines · 49 tokens per session scan A 7408bd9ffb8e
shipkit-resource-advocate is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,218 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 skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
golden-rss
Use when testing the rss golden build.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
golden-rss-empty
Use when testing the empty rss golden build.
market-research-workflow
Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing supported findings for a Pre-Award Agent. A…