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 richkuo/rk-skills --skill fable-orchestrategit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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/richkuo/rk-skills/fable-orchestrate)<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-orchestrate"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-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/richkuo/rk-skills/fable-orchestrate"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.01555 |
| Opus 5 | $0.00057 | $0.00777 |
| Sonnet 5 | $0.00023 | $0.00311 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
fable-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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-orchestrate
Run an ad-hoc task with Fable 5.1 as orchestrator and Sonnet 5 workers. You own decomposition, specs, every accept/reject decision, integration, and the PR; workers own only the mechanical implementation of their piece. Issue-based milestone work with Execution blocks uses milestone-workflow.
Input: a task description in prose; if none is obvious, ask what to orchestrate.
Model check: if the session model is not Fable 5.1, tell the user and ask whether to switch (/model fable) or proceed with the current model as orchestrator.
Steps
1. Decompose, biased against fan-out
Read the relevant code first, then split:
- Fewer, larger, sequential pieces by default. Parallelize only when pieces touch disjoint files. One worker doing the whole task is valid.
- Pin every interface between pieces upfront (signature, schema, event shape, route contract). Workers never invent their side of a seam.
- Each spec is self-contained for a worker with zero context: scope, exact files, acceptance criteria, non-goals, pinned interfaces, relevant repo conventions, and the exact verification command(s) the worker must run and pass before returning.
Present the decomposition briefly, then proceed; pause only for a decision only the user can make.
2. Set up the task worktree
Create the worktree per work-on-issue step 1, named cc/fable-orchestrate/<short-task-name>, with no baseRefs and with the user's targetBranch when one was named. Everything lands on this one branch; one PR is the deliverable regardless of worker count.
3. Dispatch workers
| Shape | Dispatch |
|---|---|
| 1–2 sequential pieces | Agent calls, subagent_type: general-purpose, model: sonnet, run_in_background: false when the next piece depends on it. Workers build in the task worktree (path stated in the spec). Commit each accepted piece before dispatching the next; step 4's reset restores to committed HEAD. |
| Fan-out (3+ parallel pieces, disjoint files) | A Workflow script (invoking this skill is the user's opt-in). Implementation agent() calls pass model: 'sonnet' and isolation: 'worktree'; judgment stages omit the model override to inherit Fable. Isolated worktrees are auto-cleaned when unchanged, so each spec instructs the worker to commit on the branch cc/fable-orchestrate/<short-task-name>/worker-<n>-r<round> (-r0 first; each step 4 re-dispatch increments it) and return that branch name or an explicit "no changes". A result with neither has failed; re-dispatch under the step 4 cap. |
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.
- 4d ago Changed · -6 lines 27a32f4aa387
- 6d ago Changed · -12 lines · -10 tokens per session 75e38e5481f6
- 10d ago First seen · 92 lines · 125 tokens per session scan A 17d03d976fc9
fable-orchestrate is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 1,555 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
issue-fields-migration
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say "migrate my labels to issue fields", "migrate project fields to issue fields", "convert labels to issue fields", "copy project field values to issue fields"…
flowstudio-power-automate-governance
Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load…
gtm-enterprise-account-planning
Strategic account planning and execution for enterprise deals. Use when planning complex sales cycles, managing multiple stakeholders, applying MEDDICC qualification, tracking deal health, or building mutual action plans. Includes the "stale MAP equals dead deal" pattern.
gtm-enterprise-onboarding
Four-phase framework for onboarding enterprise customers from contract to value realization. Use when implementing new enterprise customers, preventing churn during onboarding, or solving the adoption cliff that kills deals post-go-live. Includes the Week 4 ghosting pattern.
gtm-operating-cadence
Design meeting rhythms, metric reporting, quarterly planning, and decision-making velocity for scaling companies. Use when decisions are slow, planning is broken, the company is growing but alignment is worse, or leadership meetings consume all time without producing decisions.