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 aster-configgit 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/aster-config)<a href="https://agentmods.dev/skills/zfinix/aster/aster-config"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-config/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/aster-config"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-config.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 | $0.00065 | $0.01199 |
| Opus 5.5 | $0.00026 | $0.00480 |
| Sonnet 5.5 | $0.00013 | $0.00240 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
aster-config scanned grade A with 1 finding 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 14d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
use_default_rules: true # ask on .git/**, workflows; ask on sudo/rm/curl in `auto`; refuse secret reads How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring Aster (aster.yaml)
aster init writes the global ~/.aster/aster.yaml (or aster.yaml at the repo root with --local). Every field is optional. Precedence: CLI flags > shell env > repo aster.yaml > global aster.yaml > built-in defaults. aster config path shows which files apply here. API keys are NEVER read from this file; they come from ASTER_API_KEY or the key stored by aster init / aster login, so aster.yaml is safe to commit.
Review block
review:
model: openai/gpt-4o-mini # fallback for stages with no override
base_url: https://openrouter.ai/api/v1 # any OpenAI-compatible provider
hypothesis_model: deepseek/deepseek-v4-flash # cheap, high-recall pass
verify_model: anthropic/claude-sonnet-5 # independent adversarial verify
min_confidence: 0.6 # drop findings below this (0.0-1.0)
max_diff_bytes: 200000 # cap the diff sent to the model
analyzers: [] # [semgrep], [ast-grep], or both
focus_areas: [correctness, security] # bias the hypothesis pass
include: [] # empty = everything except exclude
exclude: ["target/**", "node_modules/**", "**/*.lock", "**/*.min.js"]
- Split models by stage: a cheap
hypothesis_modelfor recall, a strongverify_modelfor precision.modelfills any stage without an override.ASTER_MODELenv overrides all of it for a run. analyzersadds static-analysis backends whose findings also flow through verification:semgrepneedssemgrep/opengrepon PATH;ast-grepneedsast-grep/sgon PATH plusASTER_ASTGREP_RULESpointing at a rule file.
Permissions block
Gates what the agent edits, reads, and runs:
permissions:
mode: edit # plan | manual | auto | edit | yolo (prompts need the TUI; headless denies)
allow: [] # e.g. ["Bash(cargo test:*)", "Edit(src/**)"]
ask: [] # e.g. ["Edit(migrations/**)"]
deny: [] # e.g. ["Bash(npm publish:*)", "Edit(infra/**)"]
use_default_rules: true # ask on .git/**, workflows; ask on sudo/rm/curl in `auto`; refuse secret reads
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.
- 14d ago Changed e9f3423231bb
- 1mo ago Changed · +1 lines 26fb179157b8
- 1mo ago First seen · 77 lines · 65 tokens per session scan A 6f9c752f43e4
aster-config is a skill published in the GitHub repository Zfinix/aster (131 stars, last pushed 2d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,199 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
speccrew-dev-review-backend
SpecCrew Backend Code Review Skill. Reviews backend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-desktop
SpecCrew Desktop Code Review Skill. Reviews desktop app implementation code (Electron/Tauri) against system design documents and security standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-frontend
SpecCrew Frontend Code Review Skill. Reviews web frontend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-mobile
SpecCrew Mobile Code Review Skill. Reviews mobile app implementation code against system design documents, API contracts, and platform-specific standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…