tma1-search

tma1-search is a command for Claude Code from tma1-ai/tma1. It costs 17 tokens per session (470 once invoked), scanned A, original, Apache-2.0.

A command for searching earlier coding-agent sessions in the current project and opening a matching session transcript. A transcript is the recorded conversation from that session.

In plain words
What is it for?
Use it to search past sessions by keyword, limit results by agent or date, search all projects, or read a specific session when you know its ID.
Why use it?
It helps recover decisions, code explanations, or previous work without repeating the same investigation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex; built for openclaw.

Part of the tma1 plugin — 4 skills, 2 commands shipped together

Good fit Use it to search past sessions by keyword, limit results by agent or date, search all projects, or read a specific session when you know its ID.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/tma1-ai/tma1/tma1-search
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.

Clone the repo
git clone --depth 1 https://github.com/tma1-ai/tma1

Made for: Claude Code.

Or install tma1, the plugin that ships this one along with the rest of its 4 skills, 2 commands.

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 tma1-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/tma1-ai/tma1/tma1-search/github.svg)](https://agentmods.dev/commands/tma1-ai/tma1/tma1-search)
Your own site
<a href="https://agentmods.dev/commands/tma1-ai/tma1/tma1-search"><img src="https://agentmods.dev/badge/commands/tma1-ai/tma1/tma1-search/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.

agentmods 80×15 button for tma1-search

Your own site · 80×15
<a href="https://agentmods.dev/commands/tma1-ai/tma1/tma1-search"><img src="https://agentmods.dev/badge/commands/tma1-ai/tma1/tma1-search.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 470 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00470
Opus 5 $0.00009 $0.00235
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 12d ago against content hash ee86d468e9e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tma1-search 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 12d 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.

claude-plugin/commands/tma1-search.md · 37 lines

What it actually says

Full reference lives in skills/tma1-search/SKILL.md.

Parse $ARGUMENTS

  • --session <id> → skip search, call mcp__tma1__get_session_transcript with that id (full id or 6+ character prefix). Never guess an id from a bare token — commit hashes and oc: / cp: ids are indistinguishable from one.
  • Everything that isn't a flag → query.
  • --agent Xagent_source (codex · openclaw · copilotcopilot_cli · claude / ccclaude_code · self). Omit for every agent.
  • --days Nsince_min = N × 1440. Omit for the 7-day default.
  • --all-projectsproject: "*". Omit to stay in the current project.
  • No query and no --session → ask what to search for. Don't call the tool.

Then

  1. mcp__tma1__search_sessions → report matches with their snippets.
  2. mcp__tma1__get_session_transcript on the chosen session_id. If has_more is true and the answer isn't in the page, call again with next_offset.
  3. Answer by quoting the earlier session, not by summarising it.

Read match_mode before presenting results: substring means the indexed word-boundary search (which is case-sensitive) found nothing, so the query was widened to a case-folded substring scan. Say so. Empty results carry a note; report the silence rather than inventing a session.

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. 12d ago First seen · 37 lines · 17 tokens per session scan A ee86d468e9e3

Subscribe to this mod's changes

tma1-search is a command published in the GitHub repository tma1-ai/tma1 (118 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 470 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.