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.
npx skills add tma1-ai/tma1 --skill tma1-searchgit clone --depth 1 https://github.com/tma1-ai/tma1Wrote 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.
[](https://agentmods.dev/skills/tma1-ai/tma1/tma1-search)<a href="https://agentmods.dev/skills/tma1-ai/tma1/tma1-search"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/tma1-ai/tma1/tma1-search"><img src="https://agentmods.dev/badge/skills/tma1-ai/tma1/tma1-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.00802 |
| Opus 5 | $0.00051 | $0.00401 |
| Sonnet 5 | $0.00020 | $0.00160 |
| Haiku 4.5 | $0.00010 | $0.00080 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TMA1 Session Search (Codex)
TMA1 keeps every agent session on this machine — yours and other agents' — in a local database. This skill is the read path: find the session, then read it.
Invocation
/tma1-search retry backoff # keyword search, this project, last 7 days
/tma1-search flaky test --agent claude # only Claude Code's sessions
/tma1-search migration --days 30 # widen the window
/tma1-search pipeline --all-projects # every project
/tma1-search --session 3d8f1d0a # read one session directly
--session takes a full id or a prefix of 6+ characters. Do not
infer a session id from a bare token: commit hashes look identical, and
oc: / cp: ids don't look like hex at all. Anything not behind
--session is search text.
Workflow
- Search — call the
tma1MCP server'ssearch_sessionstool:query: everything that isn't a flagagent_source:--agentvalue (claude→claude_code,openclaw,copilot→copilot_cli,self); omit for every agentsince_min:--days N× 1440; omit for the 7-day defaultproject:"*"with--all-projects; otherwise omit
- Report the matches with their snippets so the user can pick. One obvious hit and a clear question → go straight to step 3.
- Read —
get_session_transcriptwith the chosensession_id.has_more: truemeans older messages exist; call again with the returnednext_offsetif the answer isn't in this page. - Answer with quotes from the earlier session, not a summary.
Reading the response
sessions[]—session_id,agent_source,last_activity_ago,hit_count,snippets[](a window around each match).match_mode—termis the indexed pass: whole words, case-sensitive.substringmeans that pass found nothing, so the search widened to a case-folded substring scan: noisier results, say so.scope_truncated: true— more sessions exist in the window than were scanned; narrow with--agentor--days.note— only when nothing matched. Report the silence; don't invent a plausible past session.
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.
- 11d ago First seen · 64 lines · 102 tokens per session scan A 2f6738892226
tma1-search is a skill published in the GitHub repository tma1-ai/tma1 (117 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 802 once invoked, about $0.0005 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.
Other skills, from other repositories
clawmetry
Real-time observability for OpenClaw agents — local dashboard + optional encrypted cloud sync. Tracks costs, tokens, sessions, tool calls, memory, crons, and system health. Access from anywhere via ClawMetry Cloud.
time-library
Use when the user refers to previous decisions, corrections, forgotten context, already-built work, install/test/release status, source-backed evidence, or next steps in ongoing work. Treat Time Library as a standing active memory routing rule: call timelibraryrecall before answering memory-dependent prompts. Also…
adam-framework
5-layer persistent memory and coherence architecture for OpenClaw agents. Solves AI amnesia and within-session drift. Built and validated over 353 sessions on a live business. No CS degree required.
engram-memory
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
note-taker
Capture decisions and facts as durable notes; use when the user makes a decision worth remembering.
afu-brain
Use Afu Brain as a MASL butler brain before executing OpenClaw or other agent tools. It turns private owner memory and human intent into safe decisions, skill routing, and approval gates.