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 SouthBridgeAI/hankweave-runtime --skill hankweave-docsgit clone --depth 1 https://github.com/SouthBridgeAI/hankweave-runtimeWrote 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/southbridgeai/hankweave-runtime/hankweave-docs)<a href="https://agentmods.dev/skills/southbridgeai/hankweave-runtime/hankweave-docs"><img src="https://agentmods.dev/badge/skills/southbridgeai/hankweave-runtime/hankweave-docs/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/southbridgeai/hankweave-runtime/hankweave-docs"><img src="https://agentmods.dev/badge/skills/southbridgeai/hankweave-runtime/hankweave-docs.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 | $0.00040 | $0.04221 |
| Opus 5 | $0.00020 | $0.02110 |
| Sonnet 5 | $0.00008 | $0.00844 |
| Haiku 4.5 | $0.00004 | $0.00422 |
Grade A, and why
hankweave-docs 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 4d 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.
curl -fL https://github.com/duckdb/duckdb/releases/download/v1.5.2/duckdb_cli-linux-amd64.zip -o /tmp/duckdb-cli.zip How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hankweave docs
Consult this skill for runtime details while building, operating, or debugging hanks. It provides the reference; the separate hank-in-the-shell skill covers end-to-end workflow methodology. This skill works independently. Run lookup commands from this skill directory, or use an absolute path to scripts/hankweave-docs.sh. This helper reads documentation; it is distinct from the hankweave runtime CLI that runs hanks. Queries build a local index on first use.
Prefer the local DuckDB helper for repeated work, exact identifiers, source and fixture evidence. If DuckDB or FTS cannot be made available, use the hosted fallback: direct HTTP search and reads of documentation only. It is slower and usually needs several network requests. Pin the requested version and supply the required agent/harness/purpose identity. Queries and identity fields are logged, so send only non-sensitive documentation questions. This is an explicit alternative, not an automatic fallback after an empty result, a corrupt pack or a version mismatch.
Setup
The helper needs Python 3.8+ and the standalone duckdb CLI on PATH; installing the Python duckdb module alone is not enough. Check python3 --version and duckdb --version. On macOS, brew install duckdb supplies the CLI. For other platforms, use the official CLI downloads.
For a Linux x86_64 sandbox, install the CLI without root access:
mkdir -p "$HOME/.local/bin"
curl -fL https://github.com/duckdb/duckdb/releases/download/v1.5.2/duckdb_cli-linux-amd64.zip -o /tmp/duckdb-cli.zip
unzip -o /tmp/duckdb-cli.zip -d "$HOME/.local/bin"
chmod +x "$HOME/.local/bin/duckdb"
export PATH="$HOME/.local/bin:$PATH"
info needs no FTS extension. Other lookups build an index and need FTS. If a proxy blocks DuckDB's extension host, use the explicit PyPI-wheel installer:
bash scripts/hankweave-docs.sh install-fts
This downloads the community-distributed duckdb-extension-fts wheel matching the installed DuckDB CLI's version and platform, extracts only its extension binary, and asks DuckDB to install and load it. It does not install or run the wheel's Python package, and it does not disable DuckDB's signature checks. The command needs pip and access to PyPI; wheel availability depends on version and platform.
What ships with it
7 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.
- 4d ago First seen · 165 lines · 40 tokens per session scan A 053a3e5d4af8
hankweave-docs is a skill published in the GitHub repository SouthBridgeAI/hankweave-runtime (135 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 4,221 once invoked, about $0.0002 per session on Opus 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 2026-09-11.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…