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.
git 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/commands/tma1-ai/tma1/tma1-peer)<a href="https://agentmods.dev/commands/tma1-ai/tma1/tma1-peer"><img src="https://agentmods.dev/badge/commands/tma1-ai/tma1/tma1-peer/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/commands/tma1-ai/tma1/tma1-peer"><img src="https://agentmods.dev/badge/commands/tma1-ai/tma1/tma1-peer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.00697 |
| Opus 5 | $0.00013 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
tma1-peer 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TMA1 Peer-Agent Lens — /tma1-peer
Full reference lives in skills/tma1-peer/SKILL.md; this file carries the
rules for the explicit-invocation path.
Parse $ARGUMENTS
- First token, if it isn't a flag → agent name:
codex·openclaw·copilot→copilot_cli·claude/cc→claude_code·self/me→ yourself ·all/*/ absent →""(every peer but you). Anything else → replyunknown agent "<X>"; available: codex, openclaw, copilot, claude, self, alland STOP. --summary→detail: "summary"·--full→detail: "full"· neither → omit (server defaults to preview).--limit N→limit(1-5, default 1; per agent when no agent is named).--since 2h/--since 90m/--since 30→since_minin minutes (default 1440).- Legacy positional form
[agent] [limit] [message_limit]still works; a bare leading integer is the limit, not an agent.
Call the tool
mcp__tma1__get_peer_sessions with the parsed values. Pass what the user
gave — don't silently fall back to defaults.
Use the response
sessions[]—session_id/agent_source/last_activity_ago/duration_minutes/tool_call_count/messages/recent_tool_names/files_touched/cwd;is_latest_for_cwdmarks your own current session on aselflookup.most_recent_session— lead your answer with it so the user knows whether the work is current.partial_failures—agent → error, present only on a failed fan-out. Check it before treating emptysessionsas silence.note— only whensessionsis empty and nothing failed.
Rules:
- Quote the peer's concrete points. Do not paraphrase.
- List
files_touchedwhen the next step is "fix what they flagged". - A message with
truncated: truewas cut — fetch the rest withmcp__tma1__get_session_transcriptfor thatsession_id. - Empty + no failures →
no recent <agent> sessions on this project in the window, then stop. - Empty + failures → name the failing peer and quote the error. Don't fabricate.
- Searching by keyword instead of by agent →
/tma1-search.
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.
- 10d ago First seen · 50 lines · 26 tokens per session scan A deba68e7b7ee
tma1-peer is a command published in the GitHub repository tma1-ai/tma1 (117 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 697 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.
Other commands, from other repositories
new-skill
Scaffold a new ClawBio skill from the official template with conformance checks.
analyse
Run a ClawBio bioinformatics analysis on user-provided genetic data.
run-demo
Run a ClawBio skill demo with built-in sample data.
list-skills
List all available ClawBio bioinformatics skills with their status and capabilities.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
recall
Search past session observations and lessons for relevant context. Wrap the memorysmartsearch and memorylessonrecall MCP tools.