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 | $0.00093 | $0.01689 |
| Opus 5.5 | $0.00037 | $0.00676 |
| Sonnet 5.5 | $0.00019 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
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 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 — 133 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 necessary reading when it forms a substantial independent branch and a worker can return the needed evidence without losing decisive nuance. Usually handle a handful of files locally. Answer related questions over a small shared corpus in one parent context. Several questions do not by themselves justify several workers. Keep raw material with the parent when subtle wording, missing behavior, or shared context would be lost in a summary. Delegate an independent difficult branch to Astra when the criteria below apply.
Compare the whole path: worker reading, parent coordination and verification, retries, and repair. If verification would repeat most of a worker's reading, prefer direct parent work or a suitably capable worker from the start.
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-6-luna |
low |
| Routine document extraction, log triage, bounded source cross-checks | gpt-6-luna |
high |
| Code tracing across modules, debugging analysis, or extraction requiring substantial interpretation | gpt-6.1-sol |
high |
| Bounded Sol branch where extra reasoning is justified by complexity | gpt-6.1-sol |
xhigh, selectively |
| Difficult independent branch or separately justified evidence review | gpt-6-astra |
high, starting point |
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.
- 1mo ago Changed · +7 lines · +5 tokens per session df09dc08d36a
- 1mo ago Changed · +28 lines · -10 tokens per session 6ba491079340
- 2mo ago First seen · 98 lines · 98 tokens per session scan A 47584c4b95ee
astra-orchestrator is a skill published in the GitHub repository czlonkowski/fables (27 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,689 once invoked, about $0.0004 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 2026-09-07.
astra-orchestrator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| astra-orchestratorczlonkowski/fables | Skill | 27 | 1mo ago | MIT | A | 93 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |