spike-describe 0.1.0
Spike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire?
Install
git clone https://github.com/ucsandman/claude-harness.git claude --plugin-dir claude-harness/labs/claude-mods/lab/spike-describe
Run in a terminal. Claude Code loads the mod from that folder for the session.
Hooks into
Nothing we recognise automatically. See the source on GitHub.
Also in ucsandman/claude-harness
- claude-runtime 0.2.0 Shared Claude runtime adapter: normalises function-hook events into ClaudeRuntimeEvent, exposes $.runtime (emit bus, supports, judge, snapshot) to other plugins, and writes a JSONL event log 29
- tunnel-cost 0.1.0 MIDDLEWARE TUNNEL stage 2: Cost analyzer: estimates the call's token cost from the args size 29
- spike-compact 0.1.0 Spike: does $.session.compact() work from a plugin, and what does the session.compact event carry? 29
- blackbox 0.1.0 BLACK BOX RECORDER: structured per-session timeline of prompts, model steps, tool calls, subagents and denials; /blackbox prints it 29
- probe3 0.1.0 Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection 29
- tunnel-telemetry 0.1.0 MIDDLEWARE TUNNEL stage 4: Telemetry: records the call and its result for the ledger 29
More other mods
- telemetry 0.1.0 Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential. 149.9k
- ruflo-mods 0.5.0 ruflo as a Claude Code mod (function hooks, ADR-404): in-process prompt routing, edit learning signals, tighten-only tool checks from ruflo policy, the cost-tracker budget ladder, a mod trust gate for newly installed mods, and the $.ruflo noun other mods compose their status with. Opt-in and remo... 74.2k
- universal-audit-log 0.2.0 One hook on * that records every event on $ (tool calls, prompts, turns, other plugins' fs/http/process calls) as JSON lines with origin plugin and tier, duration and outcome, including denials. Buffered and flushed to a JSONL file through $.fs at the end of every turn. 32.5k
- effort-modes 0.1.0 Offers three modes through mode-registry: ui (low effort), api (medium) and review (max, for code review and security). Sets the main thread's effort per mode; makes no model calls of its own. 538
- tool-list-mod 0.1.0 Probe plugin for the R3 function-hook question: answers tool.list with one named tool removed and writes one marker file per call. Used by tests/probes/function-hooks-probe.sh. 292