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/huuanh20/awesome-ai-agent-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/huuanh20/awesome-ai-agent-skills/docs-fe)<a href="https://agentmods.dev/commands/huuanh20/awesome-ai-agent-skills/docs-fe"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/docs-fe/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/huuanh20/awesome-ai-agent-skills/docs-fe"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-skills/docs-fe.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 | $0.00000 | $0.01019 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
docs-fe 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 11d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a frontend handoff document.
Input: $ARGUMENTS
Format Flag
| Flag | Output |
|---|---|
| (none) | Markdown (default) — save as {base}.md |
--html |
HTML only — save as {base}.html, no MD created |
Strip the flag before mode detection below.
Mode Selection
| Input | Mode | Scope |
|---|---|---|
| blank | git | staged + unstaged changes (git diff HEAD) |
starts with feature/ or feat/ |
feature | endpoint files matching that feature name |
ends with a file extension (.cs, .ts, .py, …) |
file | that specific file |
| any other text | keyword | search endpoint files for the keyword |
Steps
1. Resolve scope
git mode: run git diff --name-only HEAD + git diff --cached --name-only. Filter to changed files that contain endpoint/route definitions.
feature mode: search the API layer for files matching the feature name. Check CLAUDE.md for the project's API file locations; fall back to common patterns:
src/**/Api/**/*{keyword}*.cs(.NET)src/**/routes/**/*{keyword}*(Node/Express)**/views.pyor**/router.py(Python)
file mode: use the given path directly.
keyword mode: glob API layer files, then grep content for the keyword.
If no endpoint files found, stop: "No changed endpoint files found. Pass a feature name, file path, or keyword."
2. Determine commit type and title
From the resolved scope and (if git mode) recent commits git log --oneline -5, determine:
- commit type:
feat,refactor, orfix - short title in kebab-case
- date: today's date in
YYYY-MM-DD
Base filename: docs/fe/{YYYY-MM-DD}-{type}-{short-title}
3. Identify changed endpoints
Read the resolved files to list every endpoint added or modified:
- HTTP method + path
- Auth requirement (roles or "any authenticated user")
- Brief purpose (1 line)
4. Collect contracts
For each changed endpoint, read relevant DTO/schema/validator/serializer files:
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.
- 11d ago First seen · 147 lines · 0 tokens per session scan A c01efb790326
docs-fe is a command published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,019 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 2026-08-31.
Other commands, from other repositories
deapi-setup
Configure result delivery method for deAPI jobs (polling, webhooks, websockets).
generate-controller
Generate a Laravel controller following best practices.
generate-command
Génération Commande Symfony.
mcp
MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting.
ocr
Extract text from images using AI-powered OCR.
pickup
Pick up a previous hunt on a target — shows hunt history, untested endpoints, and memory-informed suggestions. Usage: /pickup target.com.