transcript

transcript is a skill for Claude Code, Codex from mrboups/xbrain. It costs 61 tokens per session (1,891 once invoked), scanned A, original, MIT.

A guided workflow for working through a meeting transcript against a specific project goal. It extracts relevant items and lets the owner decide what to keep, apply, save for later, or skip.

In plain words
What is it for?
It helps turn calls and meeting notes into a reviewed list of concrete decisions, tasks, and possible project changes.
Why use it?
It prevents a transcript from becoming an unfiltered summary or causing project changes without the owner's decision.

Skill for Claude CodeCodex

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 skills/mrboups/xbrain/transcript
Any agent
npx skills add mrboups/xbrain --skill transcript
Clone the repo
git clone --depth 1 https://github.com/mrboups/xbrain

Made for: Claude Code, Codex.

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 transcript

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrboups/xbrain/transcript.svg)](https://agentmods.dev/skills/mrboups/xbrain/transcript)
Your own site
<a href="https://agentmods.dev/skills/mrboups/xbrain/transcript"><img src="https://agentmods.dev/badge/skills/mrboups/xbrain/transcript.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,891 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 $0.00061 $0.01891
Opus 5 $0.00030 $0.00945
Sonnet 5 $0.00012 $0.00378
Haiku 4.5 $0.00006 $0.00189

Measured yesterday against content hash bd5e52ecb401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transcript 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 yesterday.

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.

.claude/skills/transcript/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work a transcript, together

The owner arrives with a transcript and a goal. This skill turns it into a list of concrete items and then triages that list with them, one decision at a time. It never decides on their behalf what enters the project.

Why this is a skill and not an agent. A subagent cannot stop mid-run to ask a question — it takes a prompt, works in isolation, and returns a report. The triage IS the point here, so the loop has to run in the conversation. The heavy reading is still delegated (step 2), because that part needs no interaction and would otherwise fill the context the triage needs.


Step 1 — Get the goal, and the transcript

The invocation carries the goal: /transcript decide what changes for phase 28.

If no goal was given, ask for it before reading anything. The goal is not decoration — it is the filter that decides what counts as relevant, and without it the extraction returns a summary instead of a work list.

Then locate the transcript: a file path in the message, a pasted block, or a file the owner names. Do not read it into this conversation yet. If it is pasted inline, write it to <HOME>/<slug>-raw.md first so the extractor can read it from disk without it living in our context twice.

<slug> is YYYY-MM-DD-<short-topic>, derived from the transcript's own date when it has one.

Where the files go depends on the project. Resolve it once, at the start, and use it everywhere below as <HOME>:

If the repo has <HOME> is Backlog goes to
.planning/ .planning/transcripts/ .planning/BACKLOG.md
neither docs/transcripts/ docs/transcripts/BACKLOG.md

This skill runs in every project, and most of them do not use .planning/. Creating that directory in a repo whose owner never chose it is how a tool leaves litter behind — and the owner then finds a planning folder they did not ask for, in a project that has its own conventions.

Check the ledger before doing anything else: if <HOME>/<slug>.md exists, this transcript was worked before. Read it, tell the owner what was already decided, and triage only what is new. Re-asking a question they already answered is the fastest way to make a tool like this annoying enough to abandon.

Read the full file on GitHub · 164 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. yesterday First seen · 164 lines · 61 tokens per session scan A bd5e52ecb401

Subscribe to this mod's changes

transcript is a skill published in the GitHub repository mrboups/xbrain (2 stars, last pushed 20d ago), licensed MIT. It adds 61 tokens to every session and 1,891 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

lemmalog

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…

JordyZomer/lemmalog · 105 tokens

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

brain-write

How to write to the INITE Brain knowledge graph from an agent loop — recordfact (with the conversationId / evidence[] grounding inputs), ingestdocument, linkentities, retractfact, recordfeedback, and the detectcontradiction preflight. Covers confidence picking, claim grounding, retract vs forget semantics, identityof…

inite-ai/inite-brain-service · 97 tokens

brain-bitemporal

How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memorydiff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").

inite-ai/inite-brain-service · 74 tokens

brain-conflict

How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status, getcompetingfacts, detectcontradiction preflight, and the human-in-the-loop adjudication workflow. Use when the timeline shows two facts disagreeing on the same predicate, or when an agent needs to decide what…

inite-ai/inite-brain-service · 78 tokens

brain-recall

Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM…

inite-ai/inite-brain-service · 81 tokens