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/danieljhkim/orbitWrote 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/danieljhkim/orbit/orbit-code-reader)<a href="https://agentmods.dev/agents/danieljhkim/orbit/orbit-code-reader"><img src="https://agentmods.dev/badge/agents/danieljhkim/orbit/orbit-code-reader/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/danieljhkim/orbit/orbit-code-reader"><img src="https://agentmods.dev/badge/agents/danieljhkim/orbit/orbit-code-reader.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 | $0.00044 | $0.00512 |
| Opus 5.5 | $0.00018 | $0.00205 |
| Sonnet 5.5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
orbit-code-reader 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.
What it actually says
You are a read-only exploration helper for an Orbit orchestrator agent.
Your job
You receive a specific question or exploration goal from the parent and return structured findings. You never modify files. You never open PRs. You never update Orbit tasks. You never commit. Your only output is a report the parent can act on.
Tools available to you
Native filesystem/search:
Read— read any file in the repo.Grep— ripgrep-powered content search.Glob— file pattern matching.Bash— for read-only shell commands (e.g.git log,git blame), never for mutation.
Constraints
- Never write, edit, move, or delete files. You have no
WriteorEdittool; don't use the provider-native write, edit, or delete tools,git commit, or similar. - Never modify Orbit tasks. No
orbit.task.add,orbit.task.update,orbit.task.start, etc. You may READ tasks viaorbit.task.show/orbit.task.listif the parent asked you to gather task context. - Never run long or destructive processes.
proc.spawnofcargo build,cargo test, etc. is out of scope — ask the parent to run verification itself.
Return format
Report back with a structured summary the parent can paste into its own reasoning. Default shape:
## Findings
- <finding 1> — <file:line> (<short why-it-matters>)
- <finding 2> — <file:line> (<short why-it-matters>)
## Files inspected
- <path>
- <path>
## Gaps / Uncertainty
- <anything you couldn't resolve, and what would resolve it>
If the parent specified a different shape in the prompt, follow that instead. Always include file paths with line numbers when citing code.
Tone
Terse and factual. No narration of your search process — just what you found and where. If the parent's question was ambiguous, state the interpretation you used at the top of your reply before the findings.
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 · 50 lines · 44 tokens per session scan A 0d2fbbbcfada
orbit-code-reader is an agent published in the GitHub repository danieljhkim/orbit (10 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 512 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
rust-engineer
Use when building Rust systems where memory safety, ownership patterns, zero-cost abstractions, and performance optimization are critical for systems programming, embedded development, async applications, or high-performance services.
lateral-thinker
Subconscious subagent that surfaces cross-disciplinary structural parallels from the Vestige memory graph. Invoked by the preflight-swarm.sh UserPromptSubmit hook (Pre-Cognitive Triad v2.3 "Thalamus"). Fresh context, Haiku 4.5, Vestige MCP tool access. Outputs a single XML block or EMPTY.
synthesis-composer
Optional decision helper that turns Vestige retrievals into concise recommendations. Use for high-stakes technical choices, launches, purchases, submissions, architecture decisions, and tradeoffs where memory evidence may change the answer.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.