agentmods.dev

PreCompact

A pre-compression hook that runs a context-capture script before an AI coding session’s context is shortened. Context compression reduces earlier conversation or working information to make room for more work.

In plain words
What is it for?
Use it to trigger context capture before automatic or manually requested compression.
Why use it?
It preserves context before automatic or manual compression, reducing the chance that useful working information is lost. The input does not describe what the script captures.

Hook

2 7mo ago A scan tokens not measured copy · 53% MIT
View the source file agenisea/turing
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/agenisea/turing/pre-compact
Clone the repo
git clone --depth 1 https://github.com/agenisea/turing
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 53% copy Near-identical to another mod 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 yesterday.

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.

Origin

This is a copy

53% identical to SessionStart — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude-code/plugins/turing/hooks/hooks.json · 22 lines

What it actually says

{
  "PreCompact": [
    {
      "matcher": "auto",
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/scripts/capture-context.sh"
        }
      ]
    },
    {
      "matcher": "manual",
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/scripts/capture-context.sh"
        }
      ]
    }
  ]
}
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. yesterday First seen · 22 lines scan A 39389a4d0eaa

Subscribe to this mod's changes

PreCompact is a hook published in the GitHub repository agenisea/turing (2 stars, last pushed 7mo 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. It is 53% identical to SessionStart, differing in 17 lines, and is treated as a copy.

Data and AIanthropicclaude-codeclaude-code-plugincontext-engineeringhuman-centered-designprompt-engineering
Related

Other hooks, from other repositories

SessionStart

Runs when a session starts, executing check-update.sh with --no-open and --format (2 commands). From rp1-run/rp1.

rp1-run/rp1 · not measured

StopFailure

Runs on the StopFailure event, executing cc10x_event_logger.py via python3. From romiluz13/cc10x.

romiluz13/cc10x · not measured

PostToolUse

Runs after a tool call finishes for ^(Bash, PowerShell)$, ^(Read, Edit and Write)$ tool calls, executing post-commit.js, context-fill.js and ledger-recall.js via node (3 commands). From V-Songbird/foreman.

V-Songbird/foreman · not measured

Stop

Runs when the agent finishes a response, executing auto_save_session.sh via bash. From walm00/business-context-os.

walm00/business-context-os · not measured

PreToolUse

Runs before the agent uses a tool for Bash, Read, Write, Edit, Glob, Grep, mcp__.*, Bash, Task, Write and Edit tool calls, executing dispatch.cjs, pre-dispatch-conflict-check.cjs, mcp-call-gate.cjs, commit-attribution.cjs, task-track-model.cjs, security-critical-warn.cjs and phase-checkpoint.cjs via node (8 commands).…

nguyenthienthanh/aura-frog · not measured

SessionStart

Runs when a session starts, executing sync_org.py and role_inject.py via python3 (2 commands). From hdk10/orgkit.

hdk10/orgkit · not measured