A command that turns a Claude Code conversation transcript into a first-person blog post through five interactive stages: parsing, story selection, outlining, drafting, and polishing.

Use it to choose a conversation, identify possible story angles, build an outline, write a blog post, and revise it with feedback.

It removes the work of finding a coherent story in a long coding conversation and shaping it into publishable prose. You review the direction and draft at several checkpoints.

retell — Command for Claude Code by oborchers/fractional-cto

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add oborchers/fractional-cto

Claude Code

/plugin install retell

Made for: Claude Code.

Or install retell, the plugin that ships this one along with the rest of its 2 skills, 1 command, 2 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/oborchers/fractional-cto/retell/github.svg)](https://agentmods.dev/commands/oborchers/fractional-cto/retell)

Your own site

<a href="https://agentmods.dev/commands/oborchers/fractional-cto/retell"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/retell/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/oborchers/fractional-cto/retell"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/retell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,283 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.03283
Opus 5.5	$0.00007	$0.01313
Sonnet 5.5	$0.00003	$0.00657
Haiku 4.5	$0.00002	$0.00328

Measured 5d ago against content hash 8302f1c122ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retell 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.

retell/commands/retell.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transform a Claude Code conversation transcript into a polished, first-person blog post. This command orchestrates a 5-stage interactive pipeline with editorial gates at every stage.

Pipeline Overview

Stage 1: PARSE    (script, 0 tokens)   → events.json + manifest.json
Stage 2: TRIAGE   (Sonnet subagent)    → angles, recommendation, context questions
  ← Author reviews, picks angle, injects context
Stage 3: OUTLINE  (Sonnet subagent)    → sections, beats, quotes, word counts
  ← Author reviews, reorders, cuts, adjusts
Stage 4: DRAFT    (you, Opus)          → full blog post
  ← Author reviews, gives feedback
Stage 5: POLISH   (you, Opus)          → revised post (repeat until satisfied)

Execution Process

If no argument provided — Discovery Mode

Run the preview script to show recent conversations:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/preview-conversations.py 15

Present the results to the user
Ask which conversation to use (by UUID prefix) using AskUserQuestion
Continue to Stage 1 with the chosen UUID

Stage 1: Parse

Run the deterministic parser — zero LLM tokens:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/parse-conversation.py <identifier> --output-dir /tmp/retell-<uuid-prefix>

Read the manifest to understand the conversation:

How many events, sessions, subagents
Token budget estimate
Any PII warnings from the parser

Present a brief summary to the user:

"Parsed 82 events across 2 sessions. 4 subagents available. ~87K signal tokens estimated."
If PII warnings exist, show them and ask how to proceed

Between Stage 1 and Stage 2: Reference Documents

After presenting the parse summary, ask the user:

"Do you have any reference documents that provide context beyond the conversation? These could be research notes, architecture docs, design specs, prior drafts, or any markdown file with background material. Provide file paths, or say 'none' to continue."

If the user provides paths:

Verify each file exists and is readable using Read
For each document, generate a brief summary:
- File name and path
- Approximate length (word count)
- Key headings (first 2 levels)
- A 2-3 sentence synopsis of the content
Present the summaries back to the user for confirmation
If total reference doc size exceeds ~50K tokens (~200K characters), warn the user and suggest prioritizing the most relevant documents
Store both the full paths and the summaries for downstream stages

Read the full file on GitHub · 222 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.

5d ago First seen · 222 lines · 17 tokens per session scan A 8302f1c122ca

Subscribe to this mod's changes

retell is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 3,283 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-13.

Writing and docs

retell

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Pipeline Overview

Execution Process

If no argument provided — Discovery Mode

Stage 1: Parse

Between Stage 1 and Stage 2: Reference Documents

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

speckit.bug.fix