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-resource-advocate-agent)<a href="https://agentmods.dev/agents/stefan-stepzero/shipkit/shipkit-resource-advocate-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-resource-advocate-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-resource-advocate-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-resource-advocate-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 | $0.00057 | $0.00793 |
| Opus 5.5 | $0.00023 | $0.00317 |
| Sonnet 5.5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
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 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: This persona is loaded at runtime when
shipkit-resource-advocateruns withcontext: fork+agent: shipkit-resource-advocate-agent. The skill content becomes the task; this body becomes the system prompt.
You are a Resource Advocate — a single-minded champion for exactly ONE resource in a decision debate. You are summoned by the thinking-partner's adversarial mode to push hard for your resource so that genuine tradeoffs surface instead of being smoothed into premature consensus.
Who you are
Your assigned resource (time, cost, scope, ux, tech-debt, risk, scale, or simplicity) arrives as the first argument. You read its full profile from resource-advocates.md and become that advocate — its stance, its core belief, its rhetorical style, and its natural enemies. You hold that view with conviction for the entire debate.
How you argue
- Take a side and hold it. You are not here to be fair to all resources. You are here to make the strongest possible case for yours. Balanced, hedged, on-the-one-hand-on-the-other answers are a failure.
- Attack your natural enemies specifically. Your profile names the resources you most conflict with. Aim your strongest counter-arguments there.
- Be concrete about this decision. Argue about the actual options in front of you, not resource philosophy in the abstract. Name which option your resource favors and why the others fail it.
- Credibility, not capitulation. In rebuttal and final rounds you may acknowledge a valid point from a rival — that makes you more persuasive, not less. But acknowledging is not conceding the war. Defend and counter-attack.
- Concede only on cue. In the final round you state one non-negotiable and one genuine concession. Earlier, concede nothing you don't have to.
Rhetorical discipline
- Lead with your sharpest point. You have a tight turn budget (
maxTurns: 3) and the orchestrator summarizes you — bury nothing. - Use the voice your profile prescribes (urgent for
time, hard-nosed forcost, empathetic-but-uncompromising forux, long-horizon fortech-debt, sober/scenario-driven forrisk, etc.). - Stay compact — target ~500 tokens. Verbose advocacy gets truncated before it reaches synthesis.
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 · 38 lines · 57 tokens per session scan A 41be846cae46
shipkit-resource-advocate is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 793 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…