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 agentmods add skills/0xmariowu/autosearch/githubnpx skills add 0xmariowu/Autosearch --skill githubgit clone --depth 1 https://github.com/0xmariowu/AutosearchWhat 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 | $0.00000 | $0.00698 |
| Opus 5 | $0.00000 | $0.00349 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
github 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 2d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Attribution
Source: self-written, plan
autosearch-0418-channels-and-skills.md§ F002c.
name: github description: Use for code-level, issue-level, and repository discovery when query involves a library, framework, or implementation detail. version: 1 languages: [en] methods:
- id: search_public_repos impl: methods/search_public_repos.py requires: [] rate_limit: {per_min: 10, per_hour: 60} fallback_chain: [search_public_repos] when_to_use: query_languages: [en, mixed] query_types: [code, library, implementation, debugging, tooling] avoid_for: [news, product-review, people] quality_hint: typical_yield: high chinese_native: false layer: leaf domains: [code-package] scenarios: [repo-search, code-reference, issue-research] model_tier: Fast experience_digest: experience.md
Overview
GitHub is the primary channel for repository discovery, issue triage, and code search across open source software. It is the right surface when the user is asking how something is implemented, which repo is authoritative, or whether a bug already exists upstream.
For autosearch, this channel anchors developer intent to concrete artifacts instead of commentary. It matters because many technical queries are better answered by repositories, issue threads, and source snippets than by generic web summaries.
When to Choose It
- Choose it when the query names a package, framework, SDK, CLI, or implementation pattern.
- Choose it for debugging signals such as open issues, regressions, workarounds, or maintainer discussion.
- Choose it when repository health, stars, forks, recent activity, and code examples are relevant.
- Prefer it over forum channels when the user wants source-of-truth implementation detail.
- Avoid it for general news, consumer reviews, or person-focused lookups.
How To Search (Planned)
search_repositories- Call the GitHub Search Repositories API with keyword and language qualifiers, then rank likely primary repos by relevance and activity.search_issues- Call the GitHub Search Issues API to find bug reports, feature requests, and maintainer responses tied to the query.search_code- Call the GitHub Search Code API for symbol names, config fragments, or error strings when implementation detail matters more than repo discovery.search_code- Normalize output around repository, path, snippet context, and canonical GitHub URLs for downstream evidence ranking.
What ships with it
2 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.
- 2d ago First seen · 63 lines · 0 tokens per session scan A 9134a81f4e83
github is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 698 tokens. 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
search
Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation for Cloudflare-protected sites (PRL, Science, Nature, Google Scholar).
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
figure
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level diagrams, phase-space trajectories…
memory
Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.
bioinformatics
Use when working on bioinformatics workflows such as alignment, variant calling, phylogenetics, or protein-structure analysis, especially across BLAST, minimap2, samtools, bcftools, MAFFT, IQ-TREE, or ESMFold.
ingest
Use when the user wants to process new papers, patents, theses, documents, or proceedings from inbox queues into the knowledge base, run the ingest pipeline, or rebuild indexes.