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.
npx agentmods add commands/marcosd4h/deepextractruntime/cache-managegit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWrote 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.
[](https://agentmods.dev/commands/marcosd4h/deepextractruntime/cache-manage)<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>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.
| Model | Per session | Once 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 |
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.
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
-
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
- Use the cache helper (
-
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.
- Use the cache helper (
-
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.
-
Purge Workspace Runs (
/cache-manage purge-runs)- Run
python .claude/helpers/cleanup_workspace.pyto delete stale workspace run directories. - Default: deletes runs older than 7 days.
- Use
--older-than Nto specify a custom age threshold (in days). - Use
--dry-runto preview what would be deleted without actually removing anything. - Also cleans up stale code-lifter state files from
.claude/agents/code-lifter/state/.
- Run
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.
- 3d ago First seen · 60 lines · 0 tokens per session scan A d8b1beb029be
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.