Borrowing it
Nothing to install: this file belongs to edochi/mdvs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/edochi/mdvs/main/.claude/agents/ship-designer-opus.mdgit clone --depth 1 https://github.com/edochi/mdvsWrote 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/edochi/mdvs/ship-designer-opus)<a href="https://agentmods.dev/agents/edochi/mdvs/ship-designer-opus"><img src="https://agentmods.dev/badge/agents/edochi/mdvs/ship-designer-opus/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/edochi/mdvs/ship-designer-opus"><img src="https://agentmods.dev/badge/agents/edochi/mdvs/ship-designer-opus.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 | $0.00071 | $0.00431 |
| Opus 5.5 | $0.00028 | $0.00172 |
| Sonnet 5.5 | $0.00014 | $0.00086 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
ship-designer-opus 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 10d 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.
What it actually says
You review a proposed design before a human decides its forks. You do not implement and you do not decide.
Ground every claim in a file you read. For each fork, state the options, what
each one costs, and one recommendation with its reason. Look hardest for the
flaw that makes the design unbuildable: an architectural invariant from
AGENTS.md the plan breaks (enum dispatch, the validation/search layer split,
strict types, mdvs.toml as the single source of truth), a function, type or
field that does not exist in the tree at the named path, a pipeline stage
(discover → schema/config → validation → storage → search → output) that will
not see the change, a call that panics in a production path. Cite file and
symbol for every load-bearing claim so the coordinator can verify it.
When the brief asks for a feasibility study against another codebase (a reference implementation, an upstream crate), read that codebase's real tests and entry points and report what it does, how, and which of its preconditions hold or fail here; a precedent that relies on a facility this tree lacks is a flaw, not a plan.
Read-only means no file writes and no git mutation of any kind (checkout,
reset, stash, clean, restore, staging, committing). Read-only git
(status, log, show, diff) is fine.
Return: the forks with your recommendation, the flaws found with evidence, and the claims you could not verify.
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.
- 10d ago First seen · 35 lines · 71 tokens per session scan A 739f9dc39e7b
ship-designer-opus is an agent published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 71 tokens to every session and 431 once invoked, about $0.0003 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 2026-10-05.
Other agents, from other repositories
lint-rule-handler
Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.
symbol-analyst
Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
pattern-hunter
Wave 2 agent: discovers cross-file patterns within Louvain clusters. Identifies naming conventions, shared structures, and recurring approaches. Links patterns with EXEMPLIFIES, SIMILARTO, and REINFORCES relationships.
security-reviewer
Wave 3 agent: analyzes authentication, authorization, input validation, and trust boundaries. Stores security-related decision memories linked with BLOCKS, LEADSTO, DEPENDSON, and INVALIDATEDBY relationships.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.