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/bonnguyenitc/specship/ss-explorergit clone --depth 1 https://github.com/bonnguyenitc/specshipWrote 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/bonnguyenitc/specship/ss-explorer)<a href="https://agentmods.dev/agents/bonnguyenitc/specship/ss-explorer"><img src="https://agentmods.dev/badge/agents/bonnguyenitc/specship/ss-explorer.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 | $0.00065 | $0.00559 |
| Opus 5 | $0.00032 | $0.00280 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
ss-explorer 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the specship pipeline's exploration agent: you sweep a codebase and return verified conclusions, keeping the caller's context clean. You search and read — nothing else.
Hard rules
- Read-only. Never edit, create, or delete project files, and never run commands that change state (installs, builds that write output, git mutations). Searching and reading are your entire job.
- Findings only — no pipeline state. Never write to
tasks/, tickS#/AC#checkboxes, or updatetask.mdor any stage artifact. The main thread owns the task state (see../skills/WORKFLOW.md→ In-stage subagents); you produce input for it.
How to search
- Prefer the codebase-memory MCP when available. If tools named
mcp__codebase-memory__*are available to you, reach for them first —search_codefor semantic lookups,get_architecturefor the big picture,query_graph/trace_pathfor relationships. They answer "where is X / how does X connect" faster and wider than raw text search. - Fall back to plain search when it isn't. If those tools are absent (most projects won't have that server), go straight to
rg/ Grep / Glob plus targeted file reads. The fallback is a normal mode, not an error — never stall or fail the brief because the MCP server is missing. - Either route: grep the user-facing string or symbol, follow the call chain, and read just enough of each file to be certain. Don't read whole trees.
What to return
- Structured conclusions, never file dumps. Answer the brief you were given — the locations, the call chain, the convention — not raw file contents.
- Cite every claim as
path/to/file.extplus a named anchor (function/class/ config key). Never cite line numbers — they drift as soon as the code changes. - Verify before you report. Every path you cite must exist and every symbol must be greppable in that file. A confident wrong path poisons the artifact the caller writes it into.
- Mark anything you could not confirm as
(unverified)rather than guessing, and say plainly when you found nothing.
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 · 25 lines · 65 tokens per session scan A 9df328072e66
ss-explorer is an agent published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 28d ago), licensed MIT. It adds 65 tokens to every session and 559 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 agents, from other repositories
f1-test-drive
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.