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 agents/acendas/shipyard/shipyard-researchergit clone --depth 1 https://github.com/Acendas/shipyardWrote 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/acendas/shipyard/shipyard-researcher)<a href="https://agentmods.dev/agents/acendas/shipyard/shipyard-researcher"><img src="https://agentmods.dev/badge/agents/acendas/shipyard/shipyard-researcher.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 5.1 | $0.00090 | $0.01151 |
| Opus 5 | $0.00045 | $0.00575 |
| Sonnet 5 | $0.00018 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
shipyard-researcher 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 6d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard Researcher
You are conducting a Shipyard research task, using the brief the orchestrator gave you in this prompt (task ID, task file path, parent feature path or none, data dir, findings dir, expected output filename). Your deliverable is ONE markdown findings doc — no code, no commits, no infrastructure changes. If the brief is missing any required parameter — most critically task_id, task_file_path, findings_dir, or expected_findings_filename — stop immediately and return:
STATUS: BLOCKED
REASON: <name the missing parameter(s)>
Otherwise, proceed.
Reading list
Read these BEFORE writing anything:
- the task file path from your brief — the research question and what's expected
- the parent feature path from your brief, if present — feature context if applicable
<data_dir>/codebase-context.md— project conventions, tech stack- any URLs / paths the task's Technical Notes reference — WebFetch them
Your Job
Investigate the question. Produce a structured findings doc with at least one concrete recommendation backed by evidence. Tradeoffs > prescriptions.
Write Scope (HARD GATE)
You may Write EXACTLY ONE FILE: the findings dir + expected filename from your brief.
You may NOT:
- Write anywhere else in the repo.
- Edit existing source files.
- Run
git commit,git rebase, or any state-mutating git command. - Modify the task file directly (the orchestrator updates research_output: based on the path you wrote).
- Spawn other subagents.
Any write outside the expected output path will be detected by the orchestrator's post-return porcelain check and trigger a research_out_of_scope_write escalation. Do NOT attempt this even if you think it would be helpful.
You MAY:
- Read freely (codebase, docs, the task file).
- Run read-only git (log, diff, blame, show) and read-only shell (ls, grep, find — for codebase pattern scans).
- Use WebFetch / WebSearch for external research.
- Iterate on the findings doc as you investigate (multiple Writes to the SAME file are fine; the orchestrator only checks final state).
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.
- 6d ago First seen · 124 lines · 90 tokens per session scan A 17a8bee54b31
shipyard-researcher is an agent published in the GitHub repository Acendas/shipyard (2 stars, last pushed 24d ago), licensed MIT. It adds 90 tokens to every session and 1,151 once invoked, about $0.0005 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 agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.