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-selfgit 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-self)<a href="https://agentmods.dev/skills/zfinix/aster/aster-self"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-self/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-self"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-self.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 | $0.00039 | $0.00943 |
| Opus 5.5 | $0.00016 | $0.00377 |
| Sonnet 5.5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
aster-self 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aster, about itself
You are Aster. Answer questions about your own files and settings from this map;
do not search the disk for them. When the answer depends on the current
directory, confirm with one command (aster config path, aster key path,
aster status) and quote what it prints. aster <command> --help is the source
of truth for flags.
Where things live
~ is the home directory (%USERPROFILE% on Windows). The data root is
$XDG_DATA_HOME/aster when that is set, otherwise ~/.local/share/aster.
| What | Global | Project (repo root) |
|---|---|---|
| Config | ~/.aster/aster.yaml |
aster.yaml (or aster.yml, .aster.yaml) |
| API keys | ~/.aster/.env |
.env |
| MCP servers | ~/.aster/mcp.json |
.mcp.json, or mcp.servers in aster.yaml |
| Model policy | ~/.aster/mom.yaml |
mom.yaml, then .agents/mom.yaml |
| Scheduled runs | ~/.aster/cron/ |
cron block in aster.yaml |
| Skills | ~/.local/share/aster/skills/<name>/SKILL.md |
.aster/skills/<name>/SKILL.md |
| Sub-agents | ~/.local/share/aster/agents/ |
.aster/agents/ |
| Plugins | ~/.local/share/aster/plugins/ |
.aster/plugins/ |
| Instructions | ~/.local/share/aster/AGENTS.md (also CLAUDE.md, ASTER.md) |
AGENTS.md, CLAUDE.md, ASTER.md |
| Memory | ~/.local/share/aster/memory/ |
ASTER.md |
| Sessions | ~/.local/share/aster/sessions/<repo-slug>/ |
|
| Sign-ins | ~/.local/share/aster/credentials.json |
A project file wins over the global one. For settings the order is CLI flags,
then shell env, then the project aster.yaml, then the global one, then
defaults. A project skill shadows a global skill of the same name. API keys are
never read from aster.yaml.
Changing things
Prefer these commands over hand-editing: they check the file still parses.
- Settings:
aster config listshows every key, its value, and where it came from.aster config set KEY VALUE --global|--local,aster config unset KEY,aster config edit --global|--local. Plainaster configopens a form. - Model and provider:
aster modelandaster providerlist and switch them. The default model for every repo isaster config set review.model <id> --global(the key isreview.model, notmodel). - Keys:
aster key list,aster key set VAR(prompts without echo),aster key unset VAR. These write~/.aster/.envby default;--localwrites the repo.env. There is no--globalflag onaster key. - Skills:
aster skills add <owner/repo|path|agent> [-p],aster skills list,aster skills remove NAME,aster skills init NAME. A new skill can also be written straight to the skills folder above; it loads next session. - Plugins:
aster plugins add|list|remove. - MCP:
aster mcp add|list|enable|disable|remove|login,aster mcp importto copy servers from another coding tool. - Memory:
aster remember "fact",aster memory list|add|remove|show. - Instructions: edit the
AGENTS.mdfor the scope you want. - Binary:
aster upgrade.
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.
- 10d ago First seen · 66 lines · 39 tokens per session scan A c6b3741aa718
aster-self is a skill published in the GitHub repository Zfinix/aster (129 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 943 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 2026-10-07.
Other skills, from other repositories
speccrew-knowledge-bizs-identify-entries
Analyze source directory structures to identify business module entry directories for each platform using XML workflow blocks. Use when initializing or updating business knowledge base to determine which directories contain user-facing entry points.
speccrew-knowledge-techs-generate
Stage 2 of technology knowledge initialization - Generate technology documentation for a specific platform using XML workflow blocks. Extracts tech stack, architecture, and conventions from configuration files and source code. Creates INDEX.md, tech-stack.md, architecture.md, and conventions-.md files. Used by Worker…
speccrew-knowledge-techs-index
Stage 3 of technology knowledge initialization - Generate root INDEX.md by aggregating all platform technology documents using XML workflow blocks. Creates the master index that maps platforms to their documentation and provides Agent-to-Platform mapping guide. Used by Worker Agent after all platform documents are…
speccrew-knowledge-techs-init
Stage 1 of technology knowledge initialization - Scan source code to detect technology platforms and generate techs-manifest.json using XML workflow blocks. Identifies web, mobile, backend, and desktop platforms by analyzing configuration files and project structure. Used by Worker Agent to kick off the techs pipeline.
speccrew-knowledge-bizs-dispatch
Dispatch bizs knowledge base generation tasks with 5-stage pipeline (XML Block version). Handles feature inventory, feature analysis with skill routing, graph data writing, module summarization, UI style pattern extraction, and system summary.
speccrew-knowledge-bizs-ui-graph
Constructs knowledge graph data (nodes, edges, relationships) from UI analysis results using XML workflow blocks. Generates graph JSON files and completion markers for the bizs knowledge pipeline.