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/hkuds/cli-anything/listgit 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 | $0.00000 | $0.01794 |
| Opus 5 | $0.00000 | $0.00897 |
| Sonnet 5 | $0.00000 | $0.00359 |
| Haiku 4.5 | $0.00000 | $0.00179 |
Grade A, and why
list 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cli-anything:list Command
List all available CLI-Anything tools (installed and generated).
Usage
/cli-anything:list [--path <directory>] [--depth <n>] [--json]
Options
--path <directory>- Directory to search for generated CLIs (default: current directory)--depth <n>- Maximum recursion depth for scanning (default: unlimited). Use0for current directory only,1for one level deep, etc.--json- Output in JSON format for machine parsing
What This Command Does
Displays all CLI-Anything tools available in the system:
1. Installed CLIs
Uses importlib.metadata to find installed cli-anything-* packages:
- Pattern: package name starts with
cli-anything- - Extracts: software name, version, entry point
from importlib.metadata import distributions
installed = {}
for dist in distributions():
name = dist.metadata.get("Name", "")
if name.startswith("cli-anything-"):
software = name.replace("cli-anything-", "")
version = dist.version
# Find executable via entry points or shutil.which
executable = shutil.which(f"cli-anything-{software}")
installed[software] = {
"status": "installed",
"version": version,
"executable": executable
}
2. Generated CLIs
Uses glob to find local CLI directories:
- Pattern:
**/agent-harness/cli_anything/*/__init__.py(or depth-limited variant) - Extracts: software name, version (from setup.py), source path
- Status:
generated
from pathlib import Path
import glob
import re
search_path = args.get("path", ".")
max_depth = args.get("depth", None) # None means unlimited
generated = {}
def extract_version_from_setup(setup_path):
"""Extract version from setup.py using regex."""
try:
content = Path(setup_path).read_text()
match = re.search(r'version\s*=\s*["\']([^"\']+)["\']', content)
return match.group(1) if match else None
except:
return None
def build_glob_patterns(base_path, depth):
"""Build list of glob patterns for depths 0 through max_depth.
Returns multiple patterns so that --depth 2 finds tools at depth 0, 1, AND 2.
"""
base = Path(base_path)
suffix = "agent-harness/cli_anything/*/__init__.py"
if depth is None:
# Unlimited depth: use **
return [str(base / "**" / suffix)]
# Generate patterns for all depths from 0 to max_depth
patterns = []
for d in range(depth + 1):
if d == 0:
# depth 0: look in current directory
patterns.append(str(base / suffix))
else:
# depth N: look N levels deep
prefix = "/".join(["*"] * d)
patterns.append(str(base / prefix / suffix))
return patterns
patterns = build_glob_patterns(search_path, max_depth)
for pattern in patterns:
for init_file in glob.glob(pattern, recursive=True):
parts = Path(init_file).parts
# Find cli_anything/<software> pattern
for i, p in enumerate(parts):
if p == "cli_anything" and i + 1 < len(parts):
software = parts[i + 1]
# Get agent-harness directory as source
agent_harness_idx = parts.index("agent-harness") if "agent-harness" in parts else i - 1
source = str(Path(*parts[:agent_harness_idx + 2])) # up to agent-harness
# Extract version from setup.py (setup.py is in agent-harness/, not cli_anything/)
setup_path = Path(*parts[:agent_harness_idx + 1]) / "setup.py"
version = extract_version_from_setup(setup_path)
generated[software] = {
"status": "generated",
"version": version,
"executable": None,
"source": source
}
break
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 · 238 lines · 0 tokens per session scan A c3ce736eda52
list is a command published in the GitHub repository HKUDS/CLI-Anything (48,669 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,794 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.