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 skills/hkuds/cli-anything/hermes-skillnpx skills add HKUDS/CLI-Anything --skill hermes-skillgit clone --depth 1 https://github.com/HKUDS/CLI-AnythingWhat 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 | $0.00053 | $0.01017 |
| Opus 5 | $0.00026 | $0.00508 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
cli-anything-hermes 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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI-Anything for Hermes Agent
Use this skill when the user wants Hermes Agent to act like the CLI-Anything builder.
Before implementation, use the full methodology source of truth when available:
- If this skill is being used from inside the
CLI-Anythingrepository, read../cli-anything-plugin/HARNESS.mdfirst. - If that local file is unavailable, clone or download
cli-anything-pluginfromhttps://github.com/HKUDS/CLI-Anything/tree/main/cli-anything-plugin, then useHARNESS.mdand the resources around it from that folder. - Only if both local and network retrieval fail, follow the condensed rules below.
Inputs
Accept either:
- A local source path such as
./gimpor/path/to/software - A GitHub repository URL
Derive the software name from the local directory name after cloning if needed.
Hermes Tool Bindings
Hermes agents build harnesses by combining these built-in tools:
| Tool | Role in Harness Workflow |
|---|---|
terminal |
Run shell commands, install packages, execute CLI tools, run tests |
execute_code |
Generate and write Python files (Click CLI, backend modules, tests) |
delegate_task |
Parallelize analysis or generation subtasks |
read_file / write_file |
Read and write harness source files |
patch |
Make targeted edits to generated code |
Consult the Hermes Agent documentation for the exact tool invocation syntax.
Modes
Build
Use when the user wants a new harness.
Produce this structure:
<software>/
└── agent-harness/
├── <SOFTWARE>.md
├── setup.py
└── cli_anything/
└── <software>/
├── README.md
├── __init__.py
├── __main__.py
├── <software>_cli.py
├── core/
├── utils/
└── tests/
Implement a stateful Click CLI with:
- one-shot subcommands
- REPL mode as the default when no subcommand is given
--jsonmachine-readable output- session state with undo/redo where the target software supports it
What ships with it
3 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.
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.
- yesterday First seen · 133 lines · 53 tokens per session scan A 04579318cfae
cli-anything-hermes is a skill published in the GitHub repository HKUDS/CLI-Anything (48,669 stars, last pushed 11d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,017 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…