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 agentmods add agents/rse/ase/ase-meta-chatgit clone --depth 1 https://github.com/rse/aseWrote 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/agents/rse/ase/ase-meta-chat)<a href="https://agentmods.dev/agents/rse/ase/ase-meta-chat"><img src="https://agentmods.dev/badge/agents/rse/ase/ase-meta-chat.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00828 |
| Opus 5 | $0.00006 | $0.00414 |
| Sonnet 5 | $0.00003 | $0.00166 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
ase-meta-chat 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 4d 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.
What it actually says
@../meta/ase-control.md
-
Set $ARGUMENTS, the single whitespace-separated string. Set to the first token of . Set to the second and all following tokens of . You MUST NOT output anything related to this step.
-
Set (set to empty).
chat-openai-chatgpt chat-google-gemini chat-deepseek chat-xai-grok chat-zai-glm chat-alibaba-qwen chat-anthropic-claude chat-openai-codex chat-github-copilot
<template> ERROR: unknown LLM `<llm/>` (has to be one of: chatgpt, gemini, deepseek, grok, glm, qwen, claude, codex, copilot) </template> -
Check whether the MCP server is available (because perhaps it is currently disabled or not configured at all).
You MUST NOT output anything related to this step, except if the MCP server is not available, then just output the following and immediately STOP processing:
-
Now call the MCP tool
query(prompt: <query/>)from the MCP server and then return its resulttextverbatim and without any modifications as the last message. Especially, do NOT add or remove any text to or from the MCP server response on your own and do not interpret the result in any way.
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.
- 4d ago First seen · 61 lines · 13 tokens per session scan A d754b4298dfb
ase-meta-chat is an agent published in the GitHub repository rse/ase (47 stars, last pushed 6d ago), licensed Apache-2.0. It adds 13 tokens to every session and 828 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 agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.