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 muthuishere/toolnexus --skill releasegit clone --depth 1 https://github.com/muthuishere/toolnexusWrote 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/muthuishere/toolnexus/release)<a href="https://agentmods.dev/skills/muthuishere/toolnexus/release"><img src="https://agentmods.dev/badge/skills/muthuishere/toolnexus/release/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/muthuishere/toolnexus/release"><img src="https://agentmods.dev/badge/skills/muthuishere/toolnexus/release.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 | $0.00070 | $0.02082 |
| Opus 5.5 | $0.00028 | $0.00833 |
| Sonnet 5.5 | $0.00014 | $0.00416 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade C, and why
release scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s https://pypi.org/pypi/toolnexus/json | python3 -c 'import sys,json;print(json.load(sys.stdin)["info"]["version"])' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://pypi.org/pypi/toolnexus/json | python3 -c 'import sys,json;print(json.load(sys.stdin)["info"]["version"])' How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing toolnexus
Publishing is outward-facing and irreversible: a version number can never be reused on npm, PyPI, NuGet, Maven Central, Hex or Clojars. This skill exists because the obvious signals lie in both directions — a green workflow can ship nothing, and a red workflow can be a complete success.
The two rules that override intuition
1. A green run is not evidence a package landed. ADR-0012 exists because NuGet and Maven have reported success without publishing. Always verify from outside, as a consumer would (step 6).
2. A red run is not evidence of failure. Re-dispatching a completed release makes the
already-published legs refuse a duplicate — npm cannot publish over the previously published versions, Clojars 403 redeploying non-snapshots is not allowed. That is immutability working.
Read the job list, not the conclusion.
Never do these
- Never publish unless the owner asked in this conversation. "Is it ready?" is a question, not authorization.
- Never release unmerged code. The release is cut from
mainafter the PR merges. - Never bump one port "to unblock".
preflightrefuses it, and that refusal is the point. - Never turn
ENABLE_*variables off to isolate one registry. A disabled leg is skipped silently; forgetting to restore it makes a future release quietly incomplete. Accept a red run whose only real job succeeds instead. - Never print, log, echo or paste a registry token. They are use-only env vars read at the point of use.
Steps
1. Run the readiness gate
.claude/skills/release/scripts/check-release-readiness.sh <version>
It replicates release.yml's preflight locally and adds the check preflight does not have —
that the versioned install coordinates in the docs match the release. It checks: six manifests in
lockstep (golang has none — it releases as a tag), docs install coordinates, a dated ## <version>
changelog section with a fresh ## Unreleased above it, clean tree on main in sync with origin,
the tag being free, all seven ENABLE_* gates, and licensing.
What ships with it
1 file 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.
- 1mo ago First seen · 155 lines · 70 tokens per session scan C 62881083fc59
release is a skill published in the GitHub repository muthuishere/toolnexus (5 stars, last pushed 19d ago), licensed MIT. It adds 70 tokens to every session and 2,082 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tree-sitter-language-pack
Parse and extract code intelligence from 372 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts structure/imports/exports/symbols/docstrings/comments, detects a language, runs syntax diagnostics, or produces syntax-aware chunks for LLMs — in Rust, Python…
tree-sitter-language-pack-extracting-code-structure
Use when the user wants structured code metadata from a source file — functions, classes, imports, exports, symbols, docstrings, comments, or syntax diagnostics. Covers ts-pack process feature flags, the JSON result shape, and the default feature set.
tree-sitter-language-pack-detecting-languages
Use when the user wants to know which programming language a file or snippet is. Covers implicit detection in ts-pack parse/process, confirming support with ts-pack list/info, and the SDK detection functions for path, extension, and raw content.
tree-sitter-language-pack-managing-parsers
Use when the user needs to manage the tree-sitter parser cache — prefetch parsers for offline or CI runs, list what is downloaded, inspect a language, find the cache directory, or clean it. Covers ts-pack download, list, info, cache-dir, clean, and init.
tree-sitter-language-pack-using-the-mcp-server
Use when parsing source, extracting code structure, or detecting a language through the tree-sitter-language-pack MCP server's tools, rather than shelling out to the ts-pack CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
tree-sitter-language-pack-chunking-for-llms
Use when the user wants to split source code into chunks for an LLM context window without breaking syntax mid-construct. Covers ts-pack process --chunk-size, why syntax-aware splits beat fixed-byte splits, picking a size, and the chunk JSON shape.