dump-workflow

dump-workflow is a command for coding agents from FreHu/claude-maintainability-review. It costs 21 tokens per session (306 once invoked), scanned A, original, MIT.

A command that turns the saved outputs from each agent in a workflow run into separate Markdown files and an index.

In plain words
What is it for?
Use it to inspect the newest workflow run or a chosen run by ID, save its findings to a directory, and identify outputs marked as errors.
Why use it?
It can recover individual findings when the workflow's final report fails, without asking another model to recreate the results.

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/frehu/claude-maintainability-review/dump-workflow
Clone the repo
git clone --depth 1 https://github.com/FreHu/claude-maintainability-review

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 dump-workflow

README.md
[![agentmods](https://agentmods.dev/badge/commands/frehu/claude-maintainability-review/dump-workflow.svg)](https://agentmods.dev/commands/frehu/claude-maintainability-review/dump-workflow)
Your own site
<a href="https://agentmods.dev/commands/frehu/claude-maintainability-review/dump-workflow"><img src="https://agentmods.dev/badge/commands/frehu/claude-maintainability-review/dump-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 306 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 $0.00021 $0.00306
Opus 5 $0.00010 $0.00153
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 5d ago against content hash 893c795027e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dump-workflow 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 5d 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/dump-workflow.md · 21 lines

What it actually says

Run the workflow-dump helper to recover a Workflow run's per-agent results as one markdown file per agent (plus an index). This reads the run's journal.jsonl and renders it deterministically — no model re-synthesis — so findings survive even if the final Report step crashed (e.g. a 529).

Execute:

python ~/.claude/scripts/dump-workflow.py $ARGUMENTS

Notes:

  • With no argument it picks the newest run across all sessions. Pass a wf_<id> (full or prefix) or a run-dir path to target a specific run.
  • Output goes to ./workflow-dump-<wfid>/ under the current directory unless the script is given --out <dir> (you can append that to $ARGUMENTS).
  • If python isn't found, retry with py.

After it runs, report the output directory and file count, and call out any results the script flagged as non-dict / errors (these are usually the crashed final agent). If there's an obvious headline file (e.g. a worst-boundary or a critic/investigation finding), point the user to it.

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. 5d ago First seen · 21 lines · 21 tokens per session scan A 893c795027e7

Subscribe to this mod's changes

dump-workflow is a command published in the GitHub repository FreHu/claude-maintainability-review (11 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 306 once invoked, about $0.0001 per session on Opus 5. 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.