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-advisorgit 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-advisor)<a href="https://agentmods.dev/skills/czlonkowski/fables/astra-advisor"><img src="https://agentmods.dev/badge/skills/czlonkowski/fables/astra-advisor/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-advisor"><img src="https://agentmods.dev/badge/skills/czlonkowski/fables/astra-advisor.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 | $0.00089 | $0.01015 |
| Opus 5.5 | $0.00036 | $0.00406 |
| Sonnet 5.5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
astra-advisor 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astra Advisor
Buy a small amount of GPT-6 Astra judgment at a decision point. The parent agent
gathers evidence, implements, and verifies; the advisor returns a verdict. Default
advisor: gpt-6-astra, reasoning high. Honor an explicit user model or effort
choice; do not silently substitute a different model if Astra is unavailable.
Decide whether to consult
Consult when both conditions hold:
- A wrong decision would cause substantial rework or consequences, or two genuinely different fix attempts have failed.
- There is a real choice, unresolved failure, or concrete residual concern that an independent review could resolve.
Useful moments: before committing to architecture, schema or API contracts; before finalizing a production migration; before declaring consequential work complete; before starting unattended automation that changes external state or accumulates material cost. For automation, include interval, state/deduplication, verification, stop conditions, action limits, and expected per-run cost.
Gather enough evidence to frame the question before consulting. Skip mechanical changes, settled choices, a first failed attempt, and easily cancelled read-only polling. An explicit request for an Astra second opinion overrides this relevance gate. If the parent already runs on Astra, decide locally by default; an explicitly requested independent review can still justify a separate Astra context.
Bound the exchange
- Default to one consult per task, maximum three executed advisor interactions, counting follow-ups. Use at most one reconciliation follow-up per question.
- Announce the topic, model, trigger, and count before each interaction:
Consulting GPT-6 Astra on <decision> (trigger: <reason>, interaction 1/3). - Aim for an 800-word brief; stay below 1,200 words including excerpts. Provide at most five precise file pointers. Request an answer under 300 words.
- Batch related questions. Follow up only for new evidence or a specific conflict; do not retry until the advisor agrees. Stop at the cap and explain unresolved gaps.
- These are interaction and prompt limits, not guaranteed billing caps: reasoning, tool calls, and runtime-provided context also consume resources. Respect any user spend or time limit; do not invent dollar savings from word counts.
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 First seen · 90 lines · 89 tokens per session scan A fe1dd08148ea
astra-advisor is a skill published in the GitHub repository czlonkowski/fables (26 stars, last pushed 15d ago), licensed MIT. It adds 89 tokens to every session and 1,015 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…