fast-agent is a command-line framework for creating, running, and evaluating AI agents and workflows, including connections to models, skills, and MCP servers. It is used by developers building coding tools, multimodal agents, automations, and evaluation workflows.
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 evalstate/fast-agent --skill pr-writing-reviewgit clone --depth 1 https://github.com/evalstate/fast-agentWrote 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/evalstate/fast-agent/pr-writing-review)<a href="https://agentmods.dev/skills/evalstate/fast-agent/pr-writing-review"><img src="https://agentmods.dev/badge/skills/evalstate/fast-agent/pr-writing-review.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01600 |
| Opus 5 | $0.00032 | $0.00800 |
| Sonnet 5 | $0.00013 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
pr-writing-review 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 7d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Writing Review
Extract editorial feedback from GitHub PRs to learn from review improvements.
Prerequisites
- GitHub CLI:
ghinstalled - Authenticated
ghsession:gh auth statusshould show you’re logged in- For private repos, your token needs appropriate scopes (typically
repo).
- For private repos, your token needs appropriate scopes (typically
- Python: 3.12+
- uv (recommended): https://github.com/astral-sh/uv
Division of Labor
| Tool | Responsibility |
|---|---|
| Python script | API calls, parsing, file tracking across renames, structured extraction |
| LLM analysis | Pattern recognition, paragraph comparison, style lesson synthesis |
Quick Start
> **All paths are relative to the directory containing this SKILL.md file.**
> Before running any script, first `cd` to that directory or use the full path.
# Get suggestions and feedback
uv run scripts/extract_pr_reviews.py <pr_url>
# Get full first→final comparison for deep analysis
uv run scripts/extract_pr_reviews.py <pr_url> --diff
# Same as above, but cap each FIRST/FINAL dump to 2k chars for LLM prompting
uv run scripts/extract_pr_reviews.py <pr_url> --diff --max-file-chars 2000
Workflow
Step 1: Extract with --diff
uv run scripts/extract_pr_reviews.py https://github.com/org/repo/pull/123 --diff
This outputs:
- Explicit Suggestions — exact before/after text from
suggestionblocks (supports multiple suggestion blocks per comment) - Reviewer Feedback — plain text comments (the "why" behind changes)
- File Evolution — first draft and final version of each text file
Tip: add
--max-file-chars 2000to keep each FIRST/FINAL dump lightweight, or pair--diffwith--no-filesif you only need the suggestion/feedback summaries.
Step 2: Analyze the Output
With the script output, perform this analysis:
A. Catalog the Explicit Suggestions
What ships with it
1 file 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.
- 7d ago First seen · 180 lines · 64 tokens per session scan A 9a9960b41f6d
pr-writing-review is a skill published in the GitHub repository evalstate/fast-agent (3,911 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,600 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
yfm
YAML front matter (YFM) for any markdown article. x-cmd's default is three top-level fields: tags, description, memo. Default borrows the Agent Skills frontmatter shape — see . The yfm module is a helper: x yfm ls / init / lint.
check
Comprehensive rule-based check. Triggered by "/check [target]" to evaluate all source files against project rules and report every violation.
review
Review pull requests or code changes. Triggered by "/review [prlink]" or when user asks to review pending changes.
simplify
Review code for readability, reuse, and simplicity. Triggered by "/simplify" when user wants to refactor complex code, remove duplication, or improve clarity.
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".