agentmods.dev

PreCompact

A pre-compaction hook that runs a scratchpad-size check and asks for a short checkpoint before the agent’s conversation context is compressed. A scratchpad is a file used to preserve working notes.

In plain words
What is it for?
Use it before context compaction to prune oversized notes and record progress in the branch scratchpad.
Why use it?
It preserves the current phase, completed deliverables, next action, and blockers when earlier context may no longer be available.

Hook for Claude Code

2 8d ago A scan tokens not measured original Apache-2.0
View the source file EndogenAI/dogma
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/endogenai/dogma/pre-compact
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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

PreCompact 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.

.claude/settings.json · 16 lines

What it actually says

{
  "PreCompact": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "uv run python scripts/prune_scratchpad.py --check-size 2>&1 | head -3"
        },
        {
          "type": "prompt",
          "prompt": "Write a '## Pre-Compact Checkpoint' section to the active scratchpad (at .tmp/<branch>/$(date +%Y-%m-%d).md) capturing: (1) active phase name and status, (2) all deliverables committed so far with commit SHAs, (3) the single next concrete step, (4) any open blockers. Keep it under 200 words."
        }
      ]
    }
  ]
}
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 · 16 lines scan A f7109bd6689f

Subscribe to this mod's changes

PreCompact is a hook published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. 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 2026-08-31.

AI SafetyData and AIGit and workflowProductivityagents-mdai-governanceai-harnessdogmamcp-server
Related

Other hooks, from other repositories

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing consent_gate_grant.mjs via node. From friedbotstudio/baseline.

friedbotstudio/baseline · not measured

SessionStart

Runs when a session starts, executing memory_session_start.mjs via node. From friedbotstudio/baseline.

friedbotstudio/baseline · not measured

SubagentStop

Runs when a subagent finishes, running an inline shell check. From ArdurAI/ardur.

ArdurAI/ardur · not measured

PreToolUse

Runs before the agent uses a tool for AskUserQuestion, Bash, Write, Edit, MultiEdit, NotebookEdit and Write tool calls, executing notify.mjs, destructive_cmd_guard.mjs, state_write_guard.mjs, git_commit_guard.mjs, gitignore_leak_guard.mjs, process_lifecycle_guard.mjs, setup_guard.mjs, env_guard.mjs…

friedbotstudio/baseline · not measured

PostToolUse

Runs after a tool call finishes for Write, Edit, MultiEdit and Bash tool calls, executing lint_runner.mjs, test_runner.mjs and phase_timer.mjs via node (4 commands). From friedbotstudio/baseline.

friedbotstudio/baseline · not measured

PreToolUse

Runs before the agent uses a tool, executing guard-hook.js and collector-hook.js via node (2 commands). From core0-io/nio.

core0-io/nio · not measured