runs

runs is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (1,080 once invoked), scanned A, original, MIT.

A command for browsing records from earlier workspace runs created by multi-step workflows such as triage, scanning, and reporting.

In plain words
What is it for?
Use it to list recent runs, find runs for a specific module, reopen the latest run, or inspect step summaries from a named run.
Why use it?
It lets you review existing results without running the workflow again or manually searching workspace files.

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/runs
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 runs

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/runs.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/runs)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/runs"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/runs.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 1,080 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 $0.01080
Opus 5 $0.00000 $0.00540
Sonnet 5 $0.00000 $0.00216
Haiku 4.5 $0.00000 $0.00108

Measured 3d ago against content hash a61088a2de71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runs 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/runs.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runs

Overview

Browse prior workspace runs created by multi-step workflows such as /triage, /full-report, /scan, and /batch-audit. Use this command to list the most recent runs, reopen the latest run for a module, or inspect the step summaries from a specific run without re-running the workflow.

Usage:

  • /runs -- list the 10 most recent runs
  • /runs list -- list the 10 most recent runs
  • /runs list appinfo.dll -- list recent runs for a module
  • /runs show appinfo.dll_triage_20260306_031523 -- reopen one run by ID
  • /runs latest appinfo.dll -- reopen the newest run for a module

IMPORTANT: Execution Model

Execute immediately. Do NOT ask for confirmation. Read the existing workspace artifacts and present the results directly.

Execution Context

IMPORTANT: Any inline Python that imports helpers.* must run with cd <workspace>/.claude so the .claude/ directory is on sys.path.

This command should use the helpers library rather than manually traversing JSON:

  • helpers.workspace.list_runs() for run discovery and sorting
  • helpers.workspace.read_summary() for per-step summaries
  • helpers.workspace_validation.validate_workspace_run() to validate a run

Steps

Step 0: Preflight Validation

Parse the subcommand and optional module filter:

  • No subcommand -> list
  • list [module]
  • show <run_id>
  • latest [module]

If a module filter is present for list or latest, validate it with:

from helpers.command_validation import validate_command_args
result = validate_command_args("runs", {"module": "<module>"})

If validation fails, report the errors and stop.

Step 1: /runs or /runs list [module] -- List Recent Runs

Use inline Python from .claude/:

from helpers.workspace import list_runs
runs = list_runs(module="<module_or_None>", limit=10)

Present a compact table:

Run ID Module Goal Status Updated Steps

Read the full file on GitHub · 151 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 · 151 lines · 0 tokens per session scan A a61088a2de71

Subscribe to this mod's changes

runs 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 1,080 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.