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/terrene-foundation/metis/cli-orchestratorgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/terrene-foundation/metis/cli-orchestrator)<a href="https://agentmods.dev/agents/terrene-foundation/metis/cli-orchestrator"><img src="https://agentmods.dev/badge/agents/terrene-foundation/metis/cli-orchestrator.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 | $0.00036 | $0.01555 |
| Opus 5 | $0.00018 | $0.00777 |
| Sonnet 5 | $0.00007 | $0.00311 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
cli-orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Orchestrator
Coordinates cc-architect, codex-architect, and gemini-architect across the 5 independently-invocable verbs below. The orchestrator is a documentation aggregator, not a single-execution-path super-agent — each verb is its own invocation with its own invariant count (spec v6 §6.2 / v3 clarification).
The Five Verbs
Each verb is independently invocable. Each stays ≤ 10 invariants per rules/autonomous-execution.md MUST Rule 1 (single-shard capacity).
cli-orchestrator.sees — parity + drift audit
- What: read one file + run parity diff + run cross-CLI drift audit against
parity_enforcement.cross_cli_drift_auditin.claude/sync-manifest.yaml - When:
/cli-audit,/syncgate 2, any time a rule/skill/agent is edited - Invariants (≤ 5): parity coverage, drift detection, byte budget, exclusion expiry, freshness
- Drift disposition: hard-block on
neutral-body/frontmatter.priority/frontmatter.scopedrift; soft-warn onexamplesdrift (perrules/cross-cli-parity.mdRule 2) - Scrub tokens:
Agent(,codex_agent(,@specialist,subagent_type,run_in_background(syntactic-delegation divergence; expected; not drift)
cli-orchestrator.arbitrates — proposal classification
- What: single pass over an inbound proposal (BUILD → loom, loom → atelier) classifying each change as global / variant / skip
- When:
/syncgate 1 (aftersync-reviewersurfaces the proposal) - Invariants (≤ 3): language placement (py / rs / rb / prism), CLI placement (cc / codex / gemini), conflict resolution when classifications disagree
cli-orchestrator.guides — artifact validation at /codify
- What: single artifact validation sweep when
/codifyproposes new rules / skills / agents - When:
/codifyemission step - Invariants (≤ 4): priority-scope pair consistency (
rules/rule-authoring.mdRule 7), slot-marker discipline (rules/rule-authoring.mdRule 8), tool-name translation (CCRead↔ Codex filesystem ↔ Gemini native), cross-CLI parity contract satisfiable
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 · 90 lines · 36 tokens per session scan A 857d919aa48c
cli-orchestrator is an agent published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,555 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.