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/k-dash/typemux-cc/plugin-test-cyclenpx skills add K-dash/typemux-cc --skill plugin-test-cyclegit clone --depth 1 https://github.com/K-dash/typemux-ccWhat 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 | $0.00076 | $0.01711 |
| Opus 5 | $0.00038 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade C, and why
plugin-test-cycle scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.claude/plugins/cache/typemux-cc-marketplace/ How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Test Cycle
End-to-end workflow for building, deploying, and testing the typemux-cc plugin locally. This eliminates the repetitive manual steps that are easy to forget or get wrong.
Prerequisites
- Rust toolchain installed (
cargo) - Claude Code running
- A Python project with
.venv/available for testing (e.g., rcmr_stadium subprojects)
Workflow
Step 1: Build the binary
Ask the user which version to build, or whether to just test the current code without bumping.
Option A — Build without version bump (quick iteration):
cargo build --release
The binary is at target/release/typemux-cc.
Option B — Build with version bump:
Use the /publish skill instead, then return here at Step 2.
Step 2: Record the test state
Create a resumable state note before changing Claude Code's plugin state. Record:
- repository path, branch, and commit
- whether the working tree is dirty
- test mode (local build or GitHub release)
target/release/typemux-cc --versionshasum -a 256 target/release/typemux-cc- expected marketplace source and plugin version
- each completed workflow step and its result
Store the note outside the repository, for example at
/tmp/typemux-cc-plugin-test-state.md, so it survives a restart without adding an
untracked project file. Never record credentials or environment variable values.
Step 3: Approve plugin state changes
Cache deletion, marketplace registration changes, and plugin installation mutate the user's Claude Code environment. Show the exact cache path, marketplace registration, plugin identity, and commands that will be affected, then obtain explicit user approval before each mutation. Approval for one mutation does not authorize another.
Use a dedicated local-development marketplace registration instead of replacing a
release registration when the installed Claude Code version supports naming separate
registrations. If it does not, report the limitation and ask before modifying the
existing typemux-cc-marketplace registration. Do not guess unsupported command flags.
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 · 204 lines · 76 tokens per session scan C 51c2d4b96e69
plugin-test-cycle is a skill published in the GitHub repository K-dash/typemux-cc (16 stars, last pushed 25d ago), licensed MIT. It adds 76 tokens to every session and 1,711 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcp-pyright
MCP server exposing Pyright language server functionality.
bottom-up-market-size
Size a market bottom-up from an Economic Mind market report and stress-test that number against independent sizing approaches - the headline size, the transparent per-company build (each player's revenue, share-in-market, in-market revenue, confidence and justification carried verbatim from the report), an explicit…
company-at-a-glance
Produce a rigorous, fully-sourced data snapshot of a single company - a detailed multi-year financial table (revenue, gross profit, EBITDA, EBIT, net income per year), computed margins and growth with every derived figure footnoted to its formula and inputs, plus web-sourced profile facts (founded, CEO, ownership…
competitor-benchmarking
Benchmark a set of companies against each other on hard financials - a detailed per-year data table for each company (revenue, gross profit, EBITDA, EBIT, net income), plus a cross-company summary of size, growth and profitability, with every derived figure footnoted to its formula and inputs and every line attributed…
getting-started
Orient a user to the Economic Mind plugin and connector - what it is, what data it draws on, which skills and connector tools are available, how to trigger them, and what to expect as the product grows. Use whenever the user is new to Economic Mind or asks what it is / what it can do / how to use it / how to get…
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.