Holds a session inside the task it was given: one open task with the files it may touch and the command that ends it, a guard that refuses writes outside that list, and checks that each ship with a violation and a near miss so none of them counts as coverage before it has been shown to work. It mounts beside a planning tool's roadmap, enforces the session boundary and never enforces the roadmap.
Plugin collet from marketplace slag in V-Songbird/slag. 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.
check-writerWrites a new check for a project that uses collet — the mistake it catches, the check itself, and the two fixtures that prove it. Use when asked to guard a mistake that keeps happening, to add a check or guardrail, to stop an agent repeating a specific error, or when a mistake in this repository has
task-harnessMounts the collet harness into a project — the task ledger, the rules block in AGENTS.md/CLAUDE.md/.cursor/rules, and the checks directory — or reports on a project that already has one. Use when asked to set up a harness, guardrails, scope enforcement or session continuity for a repository, to adop
node
node
node
Improves agent navigation through a repository, turns session detours into approved map-file changes, and reconciles documentation and non-code development files with current behavior. Includes audit-only review, an approved layout migration, README review, host consistency and repository hygiene.
4 skills · 1 agent · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
19 skills
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
1 command · 6 agents
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
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 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.