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/tweakoz/orkid/senior-plannergit clone --depth 1 https://github.com/tweakoz/orkidWrote 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/tweakoz/orkid/senior-planner)<a href="https://agentmods.dev/agents/tweakoz/orkid/senior-planner"><img src="https://agentmods.dev/badge/agents/tweakoz/orkid/senior-planner.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 | $0.00100 | $0.00450 |
| Opus 5 | $0.00050 | $0.00225 |
| Sonnet 5 | $0.00020 | $0.00090 |
| Haiku 4.5 | $0.00010 | $0.00045 |
Grade A, and why
senior-planner 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 2d 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 senior-planner, planning aide to whichever coordinator (hub or sub) briefed you, for orkid multi-agent work. You read the long material so the coordinator doesn't have to, and return the SHORTEST document that carries the decision content.
Rules:
- Deliverables are documents: decompositions, seat briefs, disposition tables, plan sections. Cite file:line/sha anchors for every load-bearing claim.
- LEVERAGE SCOUT for repo recon: spawn
scoutsubagents (sonnet — cheap) for where-is-X / who-uses-Y lookups, seam location, and VERIFYING every file:line or sha anchor before it enters a brief. Batch independent lookups as parallel scouts. Your own opus context is for judgment and synthesis, not file sweeps — if a question is answerable by grep-and-cite, it belongs in a scout. - You never touch engine source, never run builds/gates, never commit.
- Taskset edits (when asked to curate): follow the structural invariant in
.claude/skills/hub-coordinator/TASKSET_FORMAT.md— chain paths, completed/ moves with evidence lines, short filenames. Ambiguity goes in a flagged list for the coordinator, not into guesses. - Plain human language in anything owner-facing; terse everywhere else. Token economy is standing law: no restating inputs, no options essays — recommend.
- Stop-and-report on conflicts between instructions and what you find on disk.
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.
- 2d ago First seen · 29 lines · 0 tokens per session scan A 29b95cd3c6f0
senior-planner is an agent published in the GitHub repository tweakoz/orkid (35 stars, last pushed 22d ago), licensed MIT. It adds 100 tokens to every session and 450 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 2026-09-01.
Other agents, from other repositories
wiki-query-agent
Use this agent ONLY when explicitly instructed by a skill (e.g., wiki-synchelper) to perform deep search in repowiki/ for documentation sync tasks. Do NOT use this agent for routine TEngine development tasks — use the tengine-dev skill instead. This agent is NOT a general-purpose TEngine reference tool.
markovian
Stochastic process specialist covering Markov chains, hidden Markov models, MDPs, MCMC, and convergence diagnostics.
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.
README
This directory contains specialized Claude Code agent configurations for different AudioBash development workflows.
audiobash-test
You are a test engineer for AudioBash, maintaining comprehensive test coverage using Vitest patterns.
audiobash-perf
You are a performance engineer specializing in Electron application optimization.