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-review-cigit 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-review-ci)<a href="https://agentmods.dev/skills/zfinix/aster/aster-review-ci"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-review-ci/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-review-ci"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-review-ci.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 | $0.00075 | $0.00640 |
| Opus 5 | $0.00037 | $0.00320 |
| Sonnet 5 | $0.00015 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
aster-review-ci 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aster review in CI and automation
aster review reads a diff, hypothesizes defects, verifies them against the indexed repo, and reports findings. Everything is flag-driven; nothing requires a terminal.
Picking the diff
aster review # current branch vs its base
aster review --range main..HEAD # explicit git range
aster review --diff changes.patch # a saved diff file
git diff main... | aster review --diff - # diff from stdin
aster review --pr 123 # fetch a GitHub PR's diff
--pr needs a token: --token, else GITHUB_TOKEN, else the one stored by aster login. The repo defaults to the origin remote; override with --repo owner/repo.
Machine-readable output
aster review --json # findings as one JSON array
aster review --stream # NDJSON progress events, one per line
Use --json in CI and pipe it to aster fix or your own tooling. --stream is for editors and UIs that want live progress. --tui is the interactive browser; never use it headless.
Posting to the PR
aster review --pr 123 --comment # post findings as inline PR comments
--comment implies --pr. Run it only when you intend to publish; the plain run is read-only.
Scoping and thresholds
aster review -i "src/**/*.rs" -x "**/generated/**" --min-confidence 0.7
-i/--includeoverridesincludefrom aster.yaml;-x/--excludeadds to it. Both repeatable.--min-confidence <0.0-1.0>drops weak findings; falls back to aster.yaml.--no-indexskips the symbol index for speed, at the cost of weaker verification. Prefer keeping the index in CI.--repo-root <DIR>points evidence retrieval at a checkout other than the cwd.
Minimal GitHub Actions shape
- run: aster review --pr ${{ github.event.pull_request.number }} --comment --json > findings.json
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
ASTER_API_KEY: ${{ secrets.ASTER_API_KEY }}
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.
- 9d ago First seen · 60 lines · 75 tokens per session scan A ec0c288d1a6c
aster-review-ci is a skill published in the GitHub repository Zfinix/aster (77 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 640 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
operating-infra
Author, inspect, troubleshoot, and review infrastructure across IaC, Kubernetes, cloud resources, containers, CI/CD, and Linux hosts. Use when changing Terraform/OpenTofu, Kubernetes, Helm, Kustomize, Dockerfiles, GitHub Actions workflow/job/permissions semantics, AWS, GCP, Cloud Run, BigQuery, IAM, logs, instances…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…
ci-review
Audit CI workflow architecture and effectiveness without modifying it. Use when triggers, jobs, commands, quality gates, caches, artifacts, matrices, permissions, release paths, or deployment automation may be stale, redundant, unsafe, or unjustified.
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.