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/eigenwise/eigenwise-toolshed/update-toolshednpx skills add Eigenwise/eigenwise-toolshed --skill update-toolshedgit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWrote 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/eigenwise/eigenwise-toolshed/update-toolshed)<a href="https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/update-toolshed"><img src="https://agentmods.dev/badge/skills/eigenwise/eigenwise-toolshed/update-toolshed.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00883 |
| Opus 5 | $0.00017 | $0.00441 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade B, and why
update-toolshed scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
It reads Claude Code's installed-plugin registry, refreshes only `eigenwise-toolshed`, and updates only Toolshed plugins from that marketplace at their recorded scope and project directory. It does not inspect, refresh, How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Toolshed
Run the portable updater from this plugin installation:
node "${CLAUDE_PLUGIN_ROOT}/bin/update-toolshed.js"
It reads Claude Code's installed-plugin registry, refreshes only eigenwise-toolshed, and updates only Toolshed plugins from that marketplace at their recorded scope and project directory. It does not inspect, refresh, or update third-party marketplaces or plugins. When Model Gateway is installed, it runs its stable updater, node ~/.claude/model-gateway/update.js, and surfaces that command's output. The updater downloads and verifies the proxy, swaps it by rename without asking you to close sessions, restarts it when it can, and reports the resulting state. Claude Code's registry has versions but not release notes or commit history, so the updater says that plainly instead of guessing at a changelog. Gateway wiring stays at its recorded scope: the stable updater delegates to setup, which preserves per-project .claude/settings.local.json or user-level ~/.claude/settings.json wiring and never escalates scope. Remote Control compatibility points the base URL at api.anthropic.com, so the Codex/Grok rows disappear from /model; an explicit id such as /model claude-gpt-5.6-terra still works. Gateway wiring changes apply to new Claude Code sessions, so restart affected sessions. It continues after individual failures and prints the failing commands.
Gateway rename migration
If the updater finds the retired codex-gateway install, it stops before refreshing plugins, running setup, or changing wiring. Close every Claude Code session using Codex. From a terminal, run the updater's deferred migration command from the installed Quartermaster plugin:
node "${CLAUDE_PLUGIN_ROOT}/bin/update-toolshed.js" --migrate-model-gateway --confirm-sessions-closed
It installs model-gateway at each legacy scope, moves only ~/.claude/codex-gateway state, runs setup, ensure, and doctor, rewires recorded projects, then retires the legacy registry rows. The confirmation is deliberate: the command does not stop the shared gateway or change its state while another session may still use it.
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 · 58 lines · 35 tokens per session scan B 75860f785e11
update-toolshed is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (37 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 883 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…