spike-describe
ucsandman/Agnostic-AI
Spike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire?
8,943 mods
ucsandman/Agnostic-AI
Spike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire?
ucsandman/Agnostic-AI
Spike: safe-boundary handoff (bundle written at turn.complete from the runtime bus) and $.turn.abort semantics
ucsandman/Agnostic-AI
CLAUDE RUNTIME X-RAY: wildcard inspector with filters (/xray all|tools|subagents|session|usage|ui|errors|unknown|off), a HUD above the prompt, and a black-box timeline file
ucsandman/Agnostic-AI
COSTCLAW LIVE: per-request cost, cache decay and repeated-read detection while the session runs, and it serves the Nth identical Read of an unchanged file from its own cache instead of paying for it
ucsandman/Agnostic-AI
PRODUCTION GUARD: ambient project/environment context + a transport-independent policy core (DashClaw evidence classifier + offlocal policy engine) enforced natively on tool.call and tool.check. Blocks, asks, or contains before the command runs. /prodguard
ucsandman/Agnostic-AI
SUBAGENT SUPERVISOR: routing-and-budget Mod. Rewrites a spawn's model onto the capability graph instead of denying it, keeps a measured per-agent-type token ledger in $.store, caps tool calls per subagent, and shows live subagents + the last routing decision above the prompt. /supervisor prints the routing log and the ledger.
ucsandman/Agnostic-AI
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
briangtn/claude-gfm-render
GitHub Flavored Markdown in the transcript: alerts (> [!NOTE]), task lists, strikethrough and Mermaid diagrams
FazalAAli/pi-agent-for-claude
pi agent for claude: a pi subagent type whose model steps run the pi CLI, so pi subagents and agent-team teammates live in Claude Code's own agent UI, streamed live.
Nasrallah-AL/jev-cli
Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract, rerank, match, route, locate, ask, batch), including images and screenshots,, plus verbatim Jev-guided context compaction that replaces the built-in summary.
xobotyi/cc-foundry
Keeps Claude Code's auto memory to facts that still hold: gates memory writes and sifts new entries when the session goes idle
xobotyi/cc-foundry
Reloads plugins that settings enable but Claude Code skipped at startup
xobotyi/cc-foundry
Enforces skill invocation and reference reading via SEF checkpoints
xobotyi/cc-foundry
Wall-clock and elapsed-time grounding for agent context
Sumit189/explain-claude-mod
/explain: get answers as ASD-STE100 prose, a diagram, an HTML page, or a themed explainer video (3b1b, playful-flat)
promptadvisers/claude-mods-starter-kit
Writes a cold-start handoff to handoff/ before the context fills up or compacts, and offers to resume from it in the next session.
promptadvisers/claude-mods-starter-kit
A plain-English receipt after every turn: files created, changed and deleted, by tool or via shell, with failed attempts listed apart.
promptadvisers/claude-mods-starter-kit
Context window and session cost meter, drawn above the prompt.
promptadvisers/claude-mods-starter-kit
Coral, ink and cream reskin of Claude Code with risk-coded tool rows. Toggle with /skin.
promptadvisers/claude-mods-starter-kit
See inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per lane.
promptadvisers/claude-mods-starter-kit
Route supported subagent work to Sonnet or Haiku while keeping the main conversation on its model. /router for controls.
promptadvisers/claude-mods-starter-kit
A side panel of the files this session created, with Open, Reveal in Finder and Copy path.
promptadvisers/claude-mods-starter-kit
Watch where Claude looks: a live treemap of the repo that lights up as files are read, searched and edited.
promptadvisers/claude-mods-starter-kit
Explicit bookmarks for Claude Code sessions you want to come back to. /bm saves one, /bm open lists them with a copyable resume command.
No tracking cookies, no third-party scripts. How we handle data