transcript

A command for exporting or searching locally cached conversation transcripts, which are saved copies of past coding-agent sessions.

In plain words
What is it for?
Use it to create a scrubbed Markdown copy of a session or search Claude or Codex conversations using filters.
Why use it?
It makes sessions easier to share or find while anonymizing exports by default. It reads existing cached data and does not re-import conversations.

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/omrikais/cctally/transcript
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
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 3,260 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 $0.03260
Opus 5 $0.00000 $0.01630
Sonnet 5 $0.00000 $0.00652
Haiku 4.5 $0.00000 $0.00326

Measured yesterday against content hash 33e265dbfc41, 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.

docs/commands/transcript.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

transcript

Export or search conversation transcripts from the local cache. transcript export produces an anonymized-by-default Markdown copy of a whole session — the same scrub the dashboard's Export ▾ menu applies — so the natural "share this session" action is safe by default. transcript search is a scriptable front end to the dashboard's cross-session search.

Both subcommands read the conversation store (~/.local/share/cctally/conversations.db, populated by the dashboard or cctally cache-sync). Conversation readers attach compact accounting metadata from cache.db read-only when needed; core accounting never attaches the transcript store. The commands do not re-ingest, so the transcript reflects the current cached state.

Both sources are addressable. export takes either a Claude sessionId or an opaque v1. conversation key (Codex conversations are only addressable by their v1. key); search picks the provider with --source {claude,codex} (default claude). Absent qualification, the Claude behavior is byte-identical to before.

Claude cost coverage: Claude conversation cost metadata and search cost filters are transcript-derived lower bounds, not exact /usage billing totals. Codex accounting is unaffected.

The CLI exports one resolved conversation at a time. The dashboard's mixed-source comparison copy action composes two such whole exports as separate source-labelled Run A / Run B sections; it does not merge provider transcript bodies or invent a combined CLI source.

Synopsis

cctally transcript export <id> [--scope {all,prompts,chat,recipe}] [--raw]
                               [--speed {auto,standard,fast}] [--account REF]
                               [-o PATH]
cctally transcript search <query> [--source {claude,codex}]
                                  [--account REF]
                                  [--kind {all,prompts,assistant,tools,thinking,title,files}]
                                  [--limit N] [--offset N] [--cursor TOKEN]
                                  [--project LABEL ...] [--model FAMILY ...]
                                  [--date-from YYYY-MM-DD] [--date-to YYYY-MM-DD]
                                  [--cost-min USD] [--cost-max USD] [--rebuild-min N]
                                  [--json]

Read the full file on GitHub · 159 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 · 159 lines · 0 tokens per session scan A 33e265dbfc41

Subscribe to this mod's changes

transcript is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,260 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 2026-08-31.