agentmods.dev

SessionStart

A session-start hook that synchronizes Memex notes and reports how many knowledge cards are grouped in its index. Memex is a system for storing and recalling reusable project knowledge.

In plain words
What is it for?
It helps refresh the knowledge index, search past notes about the current topic, and remind the agent to perform a later review.
Why use it?
It helps the agent remember relevant solutions from earlier work before starting a new task and prompts it to record lessons afterward.

Hook

141 +1 1mo ago A scan tokens not measured original MIT
View the source file iamtouchskyer/memex
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add hooks/iamtouchskyer/memex/session-start
Clone the repo
git clone --depth 1 https://github.com/iamtouchskyer/memex
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

SessionStart scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hooks/hooks.json · 13 lines

How it starts

The opening of the file, as written. The whole thing — 13 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "SessionStart": [
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "MEMEX_CLI_PATH=\"${CLAUDE_PLUGIN_ROOT}/dist/cli.js\"; if [ ! -f \"$MEMEX_CLI_PATH\" ]; then echo '## Memex: plugin dist not found\n\nReinstall the memex Claude Code plugin or run: `npm install -g @touchskyer/memex`'; exit 0; fi && node \"$MEMEX_CLI_PATH\" sync 2>/dev/null; TOTAL=$(node \"$MEMEX_CLI_PATH\" read index 2>/dev/null | grep -c '^\\- \\[\\[' || true); SECTIONS=$(node \"$MEMEX_CLI_PATH\" read index 2>/dev/null | awk '/^## /{ if(s) print s\" (\"c\" cards)\"; s=$0; c=0; next } /^\\- \\[\\[/{ c++ } END{ if(s) print s\" (\"c\" cards)\" }'); if [ \"$TOTAL\" -gt 0 ]; then RECALL=\"When the task touches a topic above, run \\`memex search <keyword>\\` then \\`memex read <slug>\\` for the top hits.\nDo this BEFORE writing code or starting diagnosis — your past self already solved adjacent problems.\nFor full recall: invoke the \\`memex-recall\\` skill.\"; else RECALL=\"No cards yet. Still invoke the \\`memex-recall\\` skill — keyword search may find matches even without an index.\nAfter completing work, invoke \\`memex-retro\\` to start building your knowledge base.\"; fi; echo \"## Memex Memory System Active ($TOTAL cards)\n\n### Your Knowledge Map\n$SECTIONS\n\n### Recall — before starting work\n$RECALL\nNever include actual secrets, credentials, tokens, or exact secret file contents in memex query/body arguments; use abstract descriptions or redacted examples.\n\n### Retro — after completing work\nAfter code changes, debugging, or architectural decisions: invoke \\`memex-retro\\` skill.\nAsk: 'Did I learn something reusable?' If yes, write a card.\nCard format: title, created (YYYY-MM-DD), source: retro, category. Slugs: English kebab-case.\nLanguage: match the user's CLAUDE.md preferences.\" && last_org=$(cat ~/.memex/.last-organize 2>/dev/null || true) && if [ -n \"$last_org\" ]; then days_since=$(( ($(date +%s) - $(python3 -c \"import

Read the full file on GitHub · 13 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 13 lines scan A e255b580037b

Subscribe to this mod's changes

SessionStart is a hook published in the GitHub repository iamtouchskyer/memex (141 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and contextagent-memoryai-agentai-codingclaude-codecursorknowledge-management
Related

Other hooks, from other repositories

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing iai-mcp-turn-capture.sh and iai-mcp-per-turn-recall.sh via bash (2 commands). From CodeAbra/iai-personal-memory-engine.

CodeAbra/iai-personal-memory-engine · not measured

SessionStart

Runs when a session starts, running memorix hook. From AVIDS2/memorix.

AVIDS2/memorix · not measured

PostToolUse

Runs after a tool call finishes for Edit and Write tool calls, executing check-console-log.sh, check-architecture-boundary.sh and format-typescript.sh via bash (3 commands). From alperhankendi/Ctxo.

alperhankendi/Ctxo · not measured

SessionStart

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From jnMetaCode/superpowers-zh.

jnMetaCode/superpowers-zh · not measured

SubagentStop

Runs when a subagent finishes, running leteo hook subagent-stop. From asanabrial/leteo.

asanabrial/leteo · not measured

Stop

Runs when the agent finishes a response, executing stop.sh via bash. From kage-core/Kage.

kage-core/Kage · not measured