round-trip-reconstructor

round-trip-reconstructor is an agent for Claude Code from LarsCowe/bmalph. It costs 0 tokens per session (617 once invoked), scanned A, a copy of round-trip-reconstructor, MIT.

An agent that tests whether a condensed document contains enough information to recreate the original source documents.

In plain words
What is it for?
Use it to read a distillate, identify its source documents, and reconstruct each one in an appropriate human-readable format.
Why use it?
It checks completeness without looking at the originals, making missing details and lost structure easier to detect.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/larscowe/bmalph/round-trip-reconstructor
Clone the repo
git clone --depth 1 https://github.com/LarsCowe/bmalph

Made for: Claude Code.

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 round-trip-reconstructor

README.md
[![agentmods](https://agentmods.dev/badge/agents/larscowe/bmalph/round-trip-reconstructor.svg)](https://agentmods.dev/agents/larscowe/bmalph/round-trip-reconstructor)
Your own site
<a href="https://agentmods.dev/agents/larscowe/bmalph/round-trip-reconstructor"><img src="https://agentmods.dev/badge/agents/larscowe/bmalph/round-trip-reconstructor.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 617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.00617
Opus 5 $0.00000 $0.00309
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00062

Measured 6d ago against content hash 47c83f4a3724, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

round-trip-reconstructor 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 6d 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.

Origin

This is a copy

100% identical to round-trip-reconstructor — 0 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.

bmad/core/skills/bmad-distillator/agents/round-trip-reconstructor.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Round-Trip Reconstructor Agent

Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.

Critical constraint: You receive ONLY the distillate file path. You must NOT have access to the original source documents. If you can see the originals, the test is meaningless.

Process

Step 1: Analyze the Distillate

Read the distillate file. Parse the YAML frontmatter to identify:

  • The sources list — what documents were distilled
  • The downstream_consumer — what filtering may have been applied
  • The parts count — whether this is a single or split distillate

Step 2: Detect Document Types

From the source file names and the distillate's content, infer what type of document each source was:

  • Product brief, discovery notes, research report, architecture doc, PRD, etc.
  • Use the naming conventions and content themes to determine appropriate document structure

Step 3: Reconstruct Each Source

For each source listed in the frontmatter, produce a full human-readable document:

  • Use appropriate prose, structure, and formatting for the document type
  • Include all sections the original document would have had based on the document type
  • Expand compressed bullets back into natural language prose
  • Restore section transitions and contextual framing
  • Do NOT invent information — only use what is in the distillate
  • Flag any places where the distillate felt insufficient with [POSSIBLE GAP] markers — these are critical quality signals

Quality signals to watch for:

  • Bullets that feel like they're missing context → [POSSIBLE GAP: missing context for X]
  • Themes that seem underrepresented given the document type → [POSSIBLE GAP: expected more on X for a document of this type]
  • Relationships that are mentioned but not fully explained → [POSSIBLE GAP: relationship between X and Y unclear]

Step 4: Save Reconstructions

Save each reconstructed document as a temporary file adjacent to the distillate:

  • First source: {distillate-basename}-reconstruction-1.md
  • Second source: {distillate-basename}-reconstruction-2.md
  • And so on for each source

Read the full file on GitHub · 69 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. 6d ago First seen · 69 lines · 0 tokens per session scan A 47c83f4a3724

Subscribe to this mod's changes

round-trip-reconstructor is an agent published in the GitHub repository LarsCowe/bmalph (406 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 617 tokens. A static security scan graded it A with 0 findings. It is 100% identical to round-trip-reconstructor, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

distillate-compressor

Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.

PabloLION/bmad-plugin · 0 tokens

round-trip-reconstructor

Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.

PabloLION/bmad-plugin · 0 tokens

text-editor-architect

Role: Professional word processor architect specializing in building production-grade text editors that rival Microsoft Word, Apple Pages, and Google Docs.

eddiebelaval/squire · 9 tokens

documentation-specialist

Technical documentation, API docs, guides, and examples.

FortiumPartners/ensemble · 14 tokens

epic-scoper

PLANNING SUBAGENT — scopes ONE epic into an ordered list of stories with disjoint Owned File/Module Scope boundaries, making the epic's stories safe for parallel execution by the story-author subagents that follow. Receives: one epic's requirements slice (from epics.md or the PRD cluster), the architecture document…

aj-geddes/claude-code-bmad-skills · 222 tokens

readiness-auditor

PLANNING SUBAGENT — independently audits one or more planning artifacts and returns a structured verdict of PASS, CONCERNS, or FAIL with itemized findings. Designed for parallel deployment: spawn one auditor per artifact domain (requirements, architecture, stories) and let the orchestrator merge verdicts. Use when the…

aj-geddes/claude-code-bmad-skills · 183 tokens