pev
claudePEV (Plan-Execute-Validate) agent workflow with axiom-graph integration — /pev-cycle (full) and /pev-instance (slim)
12 skills · 10 agents · hooks
Graduated plugin-hook test agents — isolates hook resolution behavior (CLAUDE_PLUGIN_ROOT vs CLAUDE_PROJECT_DIR, frontmatter vs hooks.json) with canary-file reporting and hook-input-JSON dumping
Plugin hook-spike from marketplace axiom-graph in ddpoe/axiom-graph. Commands read from the repo's manifest — 12 days ago.
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.
hook-spikeDispatches the 4 hook-spike test agents in parallel, reads canary files from /tmp/hook-spike/, and reports a pass/fail matrix showing which hook patterns resolved and what ${CLAUDE_PLUGIN_ROOT} / ${CLAUDE_PROJECT_DIR} expanded to.
hs-heartbeatOne-shot hook smoke test — dispatches the hs-heartbeat subagent, which makes one Bash call. Reports whether the plugin's PreToolUse and PostToolUse hooks fired, and what ${CLAUDE_PLUGIN_ROOT} / ${CLAUDE_PROJECT_DIR} expanded to. Use this first before hook-spike (the full matrix) — if heartbeat doesn
hs-frontmatter-plugin-rootHook-spike — tests whether ${CLAUDE_PLUGIN_ROOT} resolves in an agent's frontmatter PreToolUse hook. Triggers on Glob.
hs-frontmatter-project-dirHook-spike — tests whether ${CLAUDE_PROJECT_DIR} resolves in an agent's frontmatter PreToolUse hook. Triggers on Grep.
hs-heartbeatAbsolute-minimum hook smoke test — makes one Bash call; the plugin's hooks.json PreToolUse(Bash) and PostToolUse(Bash) both echo visible messages to stderr.
hs-hooksjson-controlHook-spike control — triggers the plugin's hooks.json PreToolUse(Read) hook. Confirms test harness + baseline hooks.json variable expansion.
hs-subagent-stopHook-spike — tests whether a SubagentStop hook declared in agent frontmatter fires with ${CLAUDE_PLUGIN_ROOT} available.
mkdir -p /tmp/hook-spike && cat > /tmp/hook-spike/input-PreToolUse-Bash.json && echo '*** HOOK-SPIKE: PreToolUse(Bash) fired ***' >&2 && printf 'fired=true\nevent=PreToolUse\npwd=%s\nCLAUDE_PLUGIN_ROO
mkdir -p /tmp/hook-spike && cat > /tmp/hook-spike/input-PreToolUse-Read.json && env | sort > /tmp/hook-spike/hooksjson-control.env && printf 'fired=true\npwd=%s\nCLAUDE_PLUGIN_ROOT=%s\nCLAUDE_PROJECT_
mkdir -p /tmp/hook-spike && cat > /tmp/hook-spike/input-PostToolUse-Bash.json && echo '*** HOOK-SPIKE: PostToolUse(Bash) fired ***' >&2 && printf 'fired=true\nevent=PostToolUse\npwd=%s\nCLAUDE_PLUGIN_
mkdir -p /tmp/hook-spike && cat > /tmp/hook-spike/input-SubagentStop.json && printf 'fired=true\nevent=SubagentStop\npwd=%s\nCLAUDE_PLUGIN_ROOT=%s\nCLAUDE_PROJECT_DIR=%s\n' "$PWD" "${CLAUDE_PLUGIN_ROO
mkdir -p /tmp/hook-spike && cat > /tmp/hook-spike/input-Stop.json && printf 'fired=true\nevent=Stop\npwd=%s\nCLAUDE_PLUGIN_ROOT=%s\nCLAUDE_PROJECT_DIR=%s\n' "$PWD" "${CLAUDE_PLUGIN_ROOT:-<UNSET>}" "${
PEV (Plan-Execute-Validate) agent workflow with axiom-graph integration — /pev-cycle (full) and /pev-instance (slim)
12 skills · 10 agents · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
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.