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 skills add LandonSchropp/agent-toolkit --skill orchestrategit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/skills/landonschropp/agent-toolkit/orchestrate)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/orchestrate"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/orchestrate/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/skills/landonschropp/agent-toolkit/orchestrate"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/orchestrate.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 | $0.00019 | $0.00650 |
| Opus 5.5 | $0.00008 | $0.00260 |
| Sonnet 5.5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
orchestrate 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 today.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate
The daily note is the source of truth for what gets worked on today. This session hands its tasks out to other agents and keeps the note in step with the work.
REQUIRED: You must invoke the following skills:
ls-notes:daily-notels-agent:dispatch
Follow the ls-agent:dispatch's instructions with the changes below.
Active Tasks
Beyond dispatch's count, also leave out:
plan-day: Planning, not work.- Parked workspaces: Ones the user isn't ready to close but isn't actively working on. For now, they're the ones whose label ends in
-parked.
The Queue
Today's unchecked tasks are the queue. Skip dispatch's parallelization step: the user picks the order, so propose tasks from the note and let them choose.
Leave out tasks no agent can do, such as errands. Those stay with the user. Your goal is to be helpful, not intrusive or annoying.
The queue grows as the user adds to the note. Alongside dispatch's watcher, run scripts/watch-daily-note.sh with the Monitor tool, at its longest timeout, and re-arm it each time it expires. It prints a line for each unchecked task that appears in today's note, including the whole new note when the day rolls over. A task added in the last couple of minutes before it expired goes unreported, so after re-arming, read the note for unchecked tasks you haven't queued yet.
A new task joins the queue: propose it if fewer than three tasks are active, and otherwise let it wait its turn. Ignore the tasks you added yourself, and any that are already active or queued, since editing a task reports it again.
Keeping the Note Current
- The user hands you work directly: The queue lives in the note, so anything that isn't trivial goes in as a task before you queue it.
- A task's workspace closes: Check its task off, unless it's already checked.
- A workspace opens for work that isn't in the note: The user chose to spend part of the day on it. If it's a real piece of the day's work, offer to add it as a task, and add nothing until they say yes. If its label doesn't make clear what it's doing, read its agent with
herdr agent read.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -20 lines · -22 tokens per session 7792575f3871
- 15d ago Changed · +28 lines 3e313009284a
- 1mo ago Changed · +5 lines 61a04286cdb0
- 1mo ago Changed · +1 lines · +4 tokens per session 5b5104833409
- 1mo ago First seen · 36 lines · 37 tokens per session scan A 9a637c9b8cb0
orchestrate is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 650 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 skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…