The marketplace's root — the conventions every persona shares and per-agent token-spend measurement read from a session's own transcripts. No git, forge, or MCP dependency. Successor to terylon-metrics.
Plugin terylon-core from marketplace terylon in janecekvit/terylon-marketplace. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
delegate-to-repo-agentsUse when a Terylon persona (developer, refactorer, debugger, a review lens, code-reviewer) is working in a target repository that ships its own agents — a stack-specific implementer, a domain reviewer, a framework specialist. Covers how to discover them, when delegating beats doing the work yourself
measure-token-spendUse when you want to know what a Claude Code run cost in tokens — per tier (main thread vs subagents) and per agent type — measured from the session's own transcripts, not from the harness's notification figures. Runs after a pipeline build, or to compare a change's cost against a baseline. Reads lo
node "${CLAUDE_PLUGIN_ROOT}/hooks/record-agent-spend.js"
Developer pipeline — from a vague idea or a user story to implemented, tested code through brainstorm → plan → build (TDD) → finish, with an autonomous leader agent, parallel review lenses, the plan format and the build loop. Also dispatches long unattended background runs that commit after every step, so an interruption costs one step. Requires terylon-git, terylon-forge, one adapter, and terylon-core.
5 skills · 9 agents
The forge port — pull request review, description, comment handling and checklist write-back, written against an operation catalog rather than one hosting platform. Ships no adapter: enable terylon-ado or terylon-github beside it. Successor to terylon-devops.
7 skills · 1 agent
Terylon itself — the owner's MCP endpoint (/mcp) as a server, and one skill per prompt it serves: briefing, hand-over, merge-gate, add-goal, review-plan, show-story. Works in any session, the terminal, SSH and Remote Control alike. Requires the TERYLON_URL environment variable; there is no default address.
6 skills · 1 MCP server
Git foundation — worktree isolation, the review engine, and the multi-lens code reviewer. No forge, no MCP server; works in any git repository. Requires terylon-core.
3 skills · 1 agent
Tester — walks a pull request test plan and its linked item acceptance criteria, exercises what can be exercised, reconciles the two, and reports what cannot. Separates executed from asserted so a tick means something. Requires terylon-forge, one adapter, and terylon-core.
3 skills · 1 agent
The Azure DevOps adapter — fills the terylon-forge port with ADO mechanics over Microsoft's remote Azure DevOps MCP server (https://mcp.dev.azure.com), signed in with OAuth as the owner. The connect skill registers it from ADO_MCP_CLIENT_ID and ADO_MCP_TENANT_ID; every call carries ADO_ORGANIZATION. No default organisation.
3 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
200 skills
Metrics collection, logging infrastructure, distributed tracing, SLO implementation, and monitoring dashboards
4 skills · 2 commands · 4 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.