cache-manage

cache-manage is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (635 once invoked), scanned A, original, MIT.

A command set for viewing, clearing, refreshing, and removing cached analysis results stored in a project's .claude/cache directory.

In plain words
What is it for?
Use it to check cache statistics, clear all or module-specific results, rerun analysis for one module, or delete old workspace run directories.
Why use it?
It helps inspect disk usage and remove stale or unwanted results when cached analysis is outdated or taking too much space.

Command

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 commands/marcosd4h/deepextractruntime/cache-manage
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cache-manage

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/cache-manage.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/cache-manage)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/cache-manage"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/cache-manage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00635
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured 3d ago against content hash d8b1beb029be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cache-manage 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 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

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.

commands/cache-manage.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cache Manage

Overview

View statistics, clear, or refresh cached analysis results stored in .claude/cache/. Caching significantly speeds up commands like /triage, /full-report, and /audit by avoiding redundant expensive computations.

Usage:

  • /cache-manage stats -- show cache size, hit rates, and oldest entries
  • /cache-manage clear -- clear all cached results
  • /cache-manage clear appinfo.dll -- clear cache for a specific module
  • /cache-manage refresh appinfo.dll -- clear and re-run common analysis for a module
  • /cache-manage purge-runs -- delete old workspace run directories
  • /cache-manage purge-runs --older-than 1 -- delete workspace runs older than 1 day

Steps

  1. View Statistics (/cache-manage stats)

    • Use the cache helper (cache_stats()) to gather metrics.
    • Present a summary:
      • Total Size: total disk space used by cache
      • File Count: number of cached JSON results
      • Module Breakdown: size and count per module
      • Oldest Entry: timestamp of the oldest cached result
  2. Clear Cache (/cache-manage clear)

    • Use the cache helper (clear_cache()) to remove files.
    • If a module is specified, only clear that module's subdirectory.
    • Report the number of files deleted.
  3. Refresh Cache (/cache-manage refresh)

    • Clear the cache for the specified module.
    • Re-run common analysis scripts to populate the cache:
      • classify_module.py (classify-functions skill)
      • build_call_graph.py (callgraph-tracer skill)
      • analyze_topology.py (generate-re-report skill)
    • This ensures the cache is fresh and ready for subsequent commands.
  4. Purge Workspace Runs (/cache-manage purge-runs)

    • Run python .claude/helpers/cleanup_workspace.py to delete stale workspace run directories.
    • Default: deletes runs older than 7 days.
    • Use --older-than N to specify a custom age threshold (in days).
    • Use --dry-run to preview what would be deleted without actually removing anything.
    • Also cleans up stale code-lifter state files from .claude/agents/code-lifter/state/.

Read the full file on GitHub · 60 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. 3d ago First seen · 60 lines · 0 tokens per session scan A d8b1beb029be

Subscribe to this mod's changes

cache-manage is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 tokens. 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.