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 czlonkowski/fables --skill astra-orchestratorgit clone --depth 1 https://github.com/czlonkowski/fablesWrote 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/czlonkowski/fables/astra-orchestrator)<a href="https://agentmods.dev/skills/czlonkowski/fables/astra-orchestrator"><img src="https://agentmods.dev/badge/skills/czlonkowski/fables/astra-orchestrator/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/czlonkowski/fables/astra-orchestrator"><img src="https://agentmods.dev/badge/skills/czlonkowski/fables/astra-orchestrator.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 | $0.00098 | $0.01199 |
| Opus 5 | $0.00049 | $0.00600 |
| Sonnet 5 | $0.00020 | $0.00240 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
astra-orchestrator 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astra Orchestrator
Keep planning, decisions, and synthesis with the parent. Move substantial,
extractable reading into smaller worker contexts. This protocol is designed for a
gpt-6-astra parent in Codex, using native sub-agents only; invoking a skill does
not change the parent model. In Claude Code, this orchestration mode is unavailable;
the astra-advisor sibling provides the Codex CLI consultation route. If running
on another model, disclose that when relevant and delegate only when the same
tradeoff makes sense. Do not label a run Astra-led unless it is.
Gate the split
Delegate when the reading is necessary, larger than a handful of files or pages, and a worker can extract the needed facts without losing decisive nuance. Handle small reads locally. Keep raw material with the parent when the judgment depends on subtle wording, missing behavior, or context a summary would erase.
This skill explicitly instructs bounded worker delegation when that gate is met and Codex permits native delegation. Honor the user's instruction to work solo or use a particular model. Do not spawn agents merely to demonstrate this skill.
Select the worker deliberately
| Work | Default model | Reasoning |
|---|---|---|
| Mechanical inventory, exact pattern extraction, link or format checks | gpt-5.6-luna |
low |
| Code tracing, log triage, source cross-checks, document extraction | gpt-5.6-terra |
medium |
| Difficult bounded reading that needs more reasoning | gpt-5.6-sol |
high |
These are starting choices, not measured task-quality guarantees. Preserve user overrides and verify availability in the active host. Do not silently substitute another model on failure. Set the model and effort on every spawn: unconfigured subagents can inherit Astra and its reasoning effort, defeating the intended split. Do not use Astra for a routine reading worker. If the work requires Astra judgment, the parent handles it or uses a separately justified independent review.
Decompose once
What ships with it
3 files 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.
- 5d ago First seen · 98 lines · 98 tokens per session scan A 47584c4b95ee
astra-orchestrator is a skill published in the GitHub repository czlonkowski/fables (24 stars, last pushed 5d ago), licensed MIT. It adds 98 tokens to every session and 1,199 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 2026-09-07.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…