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.
git clone --depth 1 https://github.com/landim32/awesome-ai-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/commands/landim32/awesome-ai-skills/install)<a href="https://agentmods.dev/commands/landim32/awesome-ai-skills/install"><img src="https://agentmods.dev/badge/commands/landim32/awesome-ai-skills/install/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/commands/landim32/awesome-ai-skills/install"><img src="https://agentmods.dev/badge/commands/landim32/awesome-ai-skills/install.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 | $0.00022 | $0.00699 |
| Opus 5 | $0.00011 | $0.00349 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade C, and why
install scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
6. Remove the temporary directory (`rm -rf "$TEMP"`). How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/install — Install Claude Code artifacts from a GitHub repo
Install the artifact folders skills/, agents/, and commands/ from a
GitHub repository into the current project's .claude/ directory.
Input
Argument: $ARGUMENTS
Accepted formats:
<user>/<repo>— shorthand; branch defaults tomain(e.g.,landim32/awesome-ai-skills).<user>/<repo>@<branch>— explicit branch (e.g.,landim32/awesome-ai-skills@develop).- Full
https://github.com/<user>/<repo>(.git)URL with optional@<branch>suffix.
If $ARGUMENTS is empty or does not parse as one of the above, ask the user
to provide a valid <user>/<repo> and stop.
Execution
-
Parse
$ARGUMENTSintoREPO_SLUG(e.g.,landim32/awesome-ai-skills) andBRANCH(defaultmain). -
Verify that
gitis available viagit --version. If not, abort with a clear error message and stop. -
Shallow-clone the repository into a temporary directory using a single Bash command:
TEMP=$(mktemp -d -t claude-install-XXXXXX) && \ git clone --depth 1 --branch "$BRANCH" --quiet "https://github.com/$REPO_SLUG.git" "$TEMP" -
Ensure
.claude/exists in the current working directory (mkdir -p .claude). -
For each folder in the fixed list
skills,agents,commands:- If
$TEMP/<folder>exists and is not empty, create.claude/<folder>/if missing and copy its contents recursively (cp -r "$TEMP/<folder>/." ".claude/<folder>/"). Collisions MUST be overwritten; files that exist only in the destination MUST be preserved. - If
$TEMP/<folder>is missing or empty, print a warning and skip it.
- If
-
Remove the temporary directory (
rm -rf "$TEMP").
Reporting
After completion, print a concise summary containing:
- The repository slug and branch that was cloned.
- For each of the three target folders: the count of files copied, or
skipped (not present in source)if the folder was missing. - The absolute path of the destination
.claude/directory.
Boundaries
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.
- 9d ago First seen · 57 lines · 22 tokens per session scan C d464973e1704
install is a command published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 699 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
skill-safety
Hostile audit of coding-agent configuration the project installed rather than wrote: skills, subagents, commands, plugins, hooks, and rule files obtained from a marketplace, a git URL, a gist, or a teammate. Assume every installed instruction file is attacker-authored until read, and that the attacker's goal is to be…
cr
Tool-driven implementation of unresolved PR/MR review comments on GitHub, GitLab or Bitbucket: fetch every comment thread plus the out-of-thread notices (review bodies, bot summaries), evaluate each for technical validity, implement valid ones one at a time with a full validation pass after each, and scan the codebase…
_conventions
Read this file before executing any command file. Every rule here applies to every command unless the command file explicitly overrides it.
agent-rules
Audits the project's agent rule configuration end-to-end: validates every rule file, classifies every rule in the root instruction file as correctly placed or misplaced, and generates concrete new-rule suggestions from audit artifacts and project conventions. Assume every rule file has defects until proven otherwise.
cache
Hostile audit of caching correctness: assume every cache serves stale data after a write, shares a key across entities that must not share one, grows without bound, and stampedes on expiry — then prove where. A cache is a correctness liability until its key, its invalidation, its bound, and its expiry behavior are all…
complexity
Forces the laziest solution that actually works — simplest, shortest, most minimal — on every coding task, and audits a diff, plan, or whole repo for over-engineering. Channel a lazy senior developer who has seen every over-engineered codebase and been paged at 3am for one: lazy means efficient, not careless, and the…