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 commands/agentopology/agentopology/validategit clone --depth 1 https://github.com/agentopology/agentopologyWhat 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 | $0.00368 |
| Opus 5 | $0.00006 | $0.00184 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
validate 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 2d 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.
This is a copy
98% identical to binding — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/validate
/parser validate
Pipeline
- develop-grammar -> grammar-engineer
- grammar-engineer -> test-engineer [when grammar-engineer.status == needs-tests]
- grammar-engineer -> doc-writer [when grammar-engineer.status == done]
- develop-binding -> binding-engineer
- binding-engineer -> test-engineer [when binding-engineer.status == needs-tests]
- binding-engineer -> doc-writer [when binding-engineer.status == done]
- develop-tests -> test-engineer
- develop-cli -> cli-engineer
- cli-engineer -> test-engineer [when cli-engineer.status == needs-tests]
- cli-engineer -> doc-writer [when cli-engineer.status == done]
- develop-docs -> doc-writer
- validate-all -> test-engineer
Agents
| Agent | Phase | Model | Role |
|---|---|---|---|
| grammar-engineer | 1 | opus | Language engineer — evolves the .at grammar, AST types, parser, validator, and reserved keywords as a cohesive unit |
| binding-engineer | 1 | opus | Binding specialist — maintains all 5 platform bindings (Claude Code, Codex, Gemini CLI, Copilot CLI, OpenClaw) and ensures backward compatibility |
| test-engineer | 2 | sonnet | Test specialist — writes comprehensive parser tests, runs vitest, validates all example .at files |
| cli-engineer | 1 | sonnet | CLI and tooling specialist — develops the agentopology CLI commands and the interactive HTML visualizer |
| doc-writer | 3 | sonnet | Documentation specialist — maintains examples, README, and docs for the open-source package |
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.
- 2d ago First seen · 32 lines · 13 tokens per session scan A 7ccf8605f64e
validate is a command published in the GitHub repository agentopology/agentopology (102 stars, last pushed 6d ago), licensed Apache-2.0. It adds 13 tokens to every session and 368 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to binding, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
release
Walk the llmwiki release process step by step.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.