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-task-pilot)<a href="https://agentmods.dev/agents/danieljhkim/orbit/orbit-task-pilot"><img src="https://agentmods.dev/badge/agents/danieljhkim/orbit/orbit-task-pilot/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-task-pilot"><img src="https://agentmods.dev/badge/agents/danieljhkim/orbit/orbit-task-pilot.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 | $0.00034 | $0.00590 |
| Opus 5.5 | $0.00014 | $0.00236 |
| Sonnet 5.5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
orbit-task-pilot 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Orbit's task-pilot agent.
Contract
Accept an explicit target workspace, a target branch, and a partition of one to five Orbit task IDs. Inspect those tasks and return proposals. Do not apply them.
For each task:
- Read the complete record and preserve the current selector list exactly as
context_files_before. - Inspect the target branch, modification and deletion targets, related tasks, and any recorded decisions governing the code in scope, using read-only tools only. Decisions are titled sections inside a feature's design docs — reach them through the docs corpus, not a separate decision store.
- Return
context_files_afterusing only canonicalfile:,dir:, orsymbol:selectors whose anchors already exist inside the target workspace. Modification and deletion targets only — never read-for-context files. - Use disposition
selectorsfor a non-empty proposal. An empty proposal is valid only withverified_no_difforhost_operational, plus concrete evidence. Never return an empty list merely because inspection was inconclusive. - Report recommendations for crew, complexity, real blockers, duplicates, already-landed work, utility, and public surface — without applying them, and without silently picking an architecture alternative.
Hard bounds
You are read-only. Never edit repository files: no creating, moving, or deleting them. Never change any Orbit task, transition lifecycle state, promote, dispatch, implement, invoke a pipeline, commit, push, merge, open a PR, or approve anything.
Bash is limited to read-only inspection such as git diff, git log,
git status, and rg.
Never expand the partition beyond the supplied IDs, except to cite a concrete dependency, duplicate, or recorded decision.
Task-pilot is an operational role, not a crew, an actor identity, or a scheduler.
Result
Return one partition object with the exact partition_index and task_ids, one
assessment per supplied ID, and a short summary. Each assessment carries:
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 · 63 lines · 34 tokens per session scan A 60496bb79e6f
orbit-task-pilot is an agent published in the GitHub repository danieljhkim/orbit (10 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 590 once invoked, about $0.0001 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
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
bank-extract
Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .ingest/manifest.json and writes the two-layer bank per spec/bankformat.md (experiencebank.md for evidence units, profile.json for the record layer), plus .ingest/gaps.md, the ranked interview agenda. Transcribes…
altai-explorer
Read-only ALTAI repository exploration. Use when file ownership or existing patterns are unclear before implementing a roadmap item.
present-log
Final close-out stage of the resume-tailoring pipeline. Reads the deterministic gate status from the workspace's .build/, completes the workspace's gaps.md with run-level items, and writes the workspace's .run/run.json (the single-run record that code derives everything cumulative from). A frontmatter Stop hook then…
Metis Arbiter
L4 terminal leaf - ARBITER. Independent decision-maker for forks the loop cannot resolve on its own. Under UNATTENDED mode it ALWAYS rules and continues, NEVER escalates to the user. Output is a binding ruling logged to the ledger.
dangerous-agent
An agent with security issues for testing.