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 Zfinix/aster --skill gpt-astragit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/gpt-astra)<a href="https://agentmods.dev/skills/zfinix/aster/gpt-astra"><img src="https://agentmods.dev/badge/skills/zfinix/aster/gpt-astra/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/zfinix/aster/gpt-astra"><img src="https://agentmods.dev/badge/skills/zfinix/aster/gpt-astra.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 | $0.00049 | $0.00442 |
| Opus 5.5 | $0.00020 | $0.00177 |
| Sonnet 5.5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
gpt-astra 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.
What it actually says
GPT-6 Astra optimization
Astra handles nuance, ambiguity, and judgment better than previous models. Instructions written for older models often over-specify, over-constrain, or burn context on things Astra does on its own.
Core principles
-
Remove what Astra already does. It runs tests, checks its work, and reads what it needs without being told. Instructions that push these behaviors waste context and can cause over-testing.
-
Loosen decision boundaries. Astra takes boundaries seriously. Strong "always ask first" language written for older models will make Astra stop where you'd want it to continue. Replace with per-workflow permission: "The local test suite uses disposable fixtures. Run it, fix failures caused by your change, and rerun without asking."
-
Define completion, not just the first step. Astra can feel tentative about how far to take a task. If the work includes "implement, inspect the result, and fix what fails," say that in the request. A requirement to stop for review after the first implementation pulls Astra toward an early stopping point.
-
Keep descriptions short. Skill descriptions compete for context. Each one should be the minimum needed to decide when to load the skill. Long descriptions get truncated, and "pick me" energy leads to wrong skill selection.
-
Use progressive disclosure. The root SKILL.md is a router. Put detailed workflows in companion files so Astra only reads what applies to the current task.
When to apply
- Writing or editing a SKILL.md for this repo
- Auditing AGENTS.md for over-specification
- Writing task prompts for Astra
- Reviewing a skill that fires too often or not enough
Companion docs
AUDIT.md— step-by-step workflow for auditing AGENTS.md and skills against Astra's capabilities. Load this when the user asks for an audit.
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.
- 1mo ago First seen · 32 lines · 49 tokens per session scan A cfed09d8c07e
gpt-astra is a skill published in the GitHub repository Zfinix/aster (133 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 442 once invoked, about $0.0002 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
harness
Use when governing a workspace's control plane, code or not — the 01-TOOLS/ tooling layer, the 02-DOCS/ chaos→knowledge wiki, the root Knowledge map. Audits it, migrates legacy XX- folders, scaffolds provider tooling, sweeps the inbox, eats a file the person hands over ("cómete este fichero", "guárdalo en la…
diagnose-windows-sandbox-acl
Use on Windows for unexpected ALEGO sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.
office-pptx
Create, read, edit, and validate PowerPoint presentations (.pptx).
office-xlsx
Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).
office-docx
Create, read, edit, and validate Word documents (.docx).
office-export-pdf
Convert an Office document to a requested PDF with LibreOffice Kit.