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 richfrem/agent-plugins-skills --skill cli-agentgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/cli-agent)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/cli-agent"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/cli-agent/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/richfrem/agent-plugins-skills/cli-agent"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/cli-agent.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 | $0.00042 | $0.01477 |
| Opus 5.5 | $0.00017 | $0.00591 |
| Sonnet 5.5 | $0.00008 | $0.00295 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
cli-agent 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Agent (cli-agent)
Unified multi-LLM task router and execution engine for external CLI agents and local models.
Contents
- Constraints • Quick Start • Backends • Workflow • Verification • Setup & Maintenance • Personas • References
Constraints
- Authorization & Isolation: Analysis uses
--isolatedto suppress hazardous flags; non-isolated execution requires explicit user authorization. With--isolated,run_agent.pywraps input in---SOURCE---…---END SOURCE---and appends the isolation instruction. Without--isolated(including--cli llama), add that instruction to the prompt yourself:"You are operating as an isolated sub-agent. Do NOT use tools. Do NOT access filesystem. Only use the provided input."
- Fail-Closed & Single Backend: Use one backend per task; halt immediately on failure without silent fallback. See fallback-tree.md and execution-contract.md.
- Reproducibility & Scope: Reuse the caller's runtime/model/effort choice; do not start an unrequested review. Record executable versions, tokens, and outputs.
Quick Start
python3 scripts/run_agent.py <personas>/security-auditor.md <input> <output> "Review supplied source." --cli claude --isolated --require-input
Supported Backends & Dispatch
| Backend | CLI Flag | Target Runtime / Engine | Dispatch Reference |
|---|---|---|---|
| Claude | --cli claude |
Claude Code CLI (Sonnet / Opus) | claude-cli-dispatch.md |
| Codex | --cli codex |
OpenAI Codex CLI (GPT-5 / o-series) | codex-cli-dispatch.md |
| Copilot | --cli copilot |
GitHub Copilot CLI | copilot-cli-dispatch.md |
| Antigravity | --cli agy |
Google Antigravity / Gemini CLI | agy-cli-dispatch.md |
| Local LLM | --cli llama |
Local Gemma 4 12B at localhost:8089 | local-llm-dispatch.md |
What ships with it
52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 2.5 KB
- references/acceptance-criteria.md 3.0 KB
- references/agy-cli-dispatch.md 2.6 KB
- references/agy-models.json 9.9 KB
- references/antigravity-directory-spec.md 3.4 KB
- references/backend-capabilities.md 2.5 KB
- references/capability-profile-contract.md 2.5 KB
- references/cheapest_models.json 795 B
- references/cheapest_models.md 1.1 KB
- references/claude-cli-dispatch.md 1.9 KB
- references/claude-directory-spec.md 3.2 KB
- references/claude-models.json 13 KB
- references/claude-settings-schema.md 2.2 KB
- references/codex-cli-dispatch.md 2.3 KB
- references/codex-models.json 8.8 KB
- references/copilot-cli-dispatch.md 3.3 KB
- references/copilot-models.json 33 KB
- references/execution-contract.md 3.5 KB
- references/fallback-tree.md 3.5 KB
- references/gemini-cli-commands.md 4.3 KB
- references/local_llm_debrief.md 8.2 KB
- references/local-llm-dispatch.md 1.9 KB
- references/local-llm-setup-deep-reference.md 11 KB
- references/map-debt.md 964 B
- references/model-catalog-maintenance.md 3.8 KB
- references/p0-codex-observation-fixture.json 1.7 KB
- references/project-capability-baseline.md 3.4 KB
- references/project-configuration-workflow.md 1.9 KB
- references/project-setup.md 2.7 KB
- references/routing_latency_findings.md 8.4 KB
- references/routing-proxy.mmd 1.5 KB
- scripts/adapters/__init__.py 291 B runs code
- scripts/adapters/claude_adapter.py 1.3 KB runs code
- scripts/adapters/copilot_adapter.py 1.8 KB runs code
- scripts/adapters/gemini_adapter.py 2.7 KB runs code
- scripts/capability_profile.py 8.1 KB runs code
- scripts/disable_global_routing.py 6.8 KB runs code
- scripts/enable_global_routing.py 11 KB runs code
- scripts/kv_cache_orchestrator.py 13 KB runs code
- scripts/model_catalog.py 5.4 KB runs code
- scripts/routing_proxy.py 24 KB runs code
- scripts/run_agent.py 22 KB runs code
- scripts/run_server.py 8.0 KB runs code
- scripts/smoke_test_kv_cache.py 6.0 KB runs code
- scripts/sync_cheapest_models.py 3.1 KB runs code
- scripts/test_capability_profile.py 8.8 KB runs code
- scripts/test_kv_cache.py 25 KB runs code
- scripts/test_model_catalog_contract.py 9.3 KB runs code
- scripts/test_routing_proxy.py 4.0 KB runs code
- scripts/test_run_agent_runtime.py 3.5 KB runs code
- scripts/test_run_agent.py 26 KB runs code
- tests/test_project_setup_contract.py 2.3 KB runs code
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 · 65 lines · 42 tokens per session scan A fcbce06a4784
cli-agent is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,477 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.
Other skills, from other repositories
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…