agentos-render: Skill for Claude Code

.agents/skills/review-and-improve/SKILL.md

review-and-improve is a skill for Claude Code, Codex from agno-agi/agentos-render. It costs 64 tokens per session (1,337 once invoked), scanned A, a copy of review-and-improve, Apache-2.0.

A repository-wide review workflow that compares documentation, configuration, registered agents, and code. It is intended for checking whether a project is ready to share publicly.

In plain words
What is it for?
Use it before a release or after structural changes to fix straightforward documentation drift and flag issues requiring manual review.
Why use it?
It finds stale paths, missing environment-variable documentation, unreachable agents, broken links, and simple contradictions after refactors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is agno-agi/agentos-render's own configuration. It tells Claude Code and Codex how to work on agentos-render itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentos-render configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/format.sh && ./scripts/validate.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to agno-agi/agentos-render. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agno-agi/agentos-render/main/.agents/skills/review-and-improve/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agno-agi/agentos-render

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review-and-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/agno-agi/agentos-render/review-and-improve/github.svg)](https://agentmods.dev/skills/agno-agi/agentos-render/review-and-improve)
Your own site
<a href="https://agentmods.dev/skills/agno-agi/agentos-render/review-and-improve"><img src="https://agentmods.dev/badge/skills/agno-agi/agentos-render/review-and-improve/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.

agentmods 80×15 button for review-and-improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/agno-agi/agentos-render/review-and-improve"><img src="https://agentmods.dev/badge/skills/agno-agi/agentos-render/review-and-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01337
Opus 5 $0.00032 $0.00668
Sonnet 5 $0.00013 $0.00267
Haiku 4.5 $0.00006 $0.00134

Measured 9d ago against content hash 704a83ac29d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-and-improve scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -sSf http://localhost:8000/health` returns 200 (Step 4 needs it). Suggest `git checkout -b review/$(date +%Y%m%d)`.
Origin

This is a copy

98% identical to review-and-improve — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/review-and-improve/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review and Improve

Coding-agent workflow: run as /review-and-improve or by describing the task.

Sweep the repo for docs accuracy, reachability, and consistency. Fix mechanical drift in place; surface the rest. AGENTS.md is the source of truth (CLAUDE.md symlinks to it).

Auto-fix: stale doc paths; example.env entries missing for vars the code reads, or stale ones nothing reads (keep those a comment marks optional/future); a registered agent or workflow missing from an architecture diagram; an agent file on disk not imported in app/main.py; a missing app/config.yaml manifest entry (draft one and flag it); broken links between docs and skills; a single-line claim in one doc contradicted by another doc or by code (fix the doc).

Flag, don't fix: section-level rewrites; code beyond imports; pyproject.toml; anything in db/, compose.yaml, Dockerfile; failing evals or live agents.

0. Preconditions

curl -sSf http://localhost:8000/health returns 200 (Step 4 needs it). Suggest git checkout -b review/$(date +%Y%m%d).

1. Scope

Restate in a few lines: README.md, AGENTS.md, example.env; .agents/skills/*/SKILL.md; app/, agents/, teams/, workflows/, db/, evals/, scripts/; compose.yaml, Dockerfile, pyproject.toml, render.yaml. Skip .venv/, caches, .git/. Fold in any concern the user names.

2. Inventory

Read first, fix once. Build the picture: registered agents/teams/workflows in app/main.py; files on disk; what app/registry.py declares and imports; env vars read (getenv(, os.environ, plus env_flag/_int_env helpers); the manifest; eval cases; register_schedules() targets; what each script does.

3. Consistency pass

Check Where
Every agent/team/workflow file is registered agents/, teams/, workflows/app/main.py
Every registered component has a manifest entry app/main.pyapp/config.yaml
Every env var in code is documented, and every documented var is read code ↔ AGENTS.md table ↔ example.env (RUNTIME_ENV is deliberately absent from example.env)
Every path and script named in docs exists and does what's claimed README.md, AGENTS.md, skills ↔ filesystem
Architecture diagram matches registrations AGENTS.md
Eval cases reference real agents and tools evals/cases.py
Every schedule hits a real workflow id app/schedules.pyworkflows/
Registry inventory prose matches app/registry.py AGENTS.md
Key Files table matches the tree AGENTS.md
Skill name: equals its folder; ../../../ links resolve; .claude/skills symlink resolves .agents/skills/
.mcp.json servers agree with the docs .mcp.json
MCP endpoint claims match mcp= in app/main.py; scripts/mcp_check.sh calls a registered agent docs ↔ code

Read the full file on GitHub · 78 lines

Changes

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.

  1. 9d ago First seen · 78 lines · 64 tokens per session scan A 704a83ac29d8

Subscribe to this mod's changes

review-and-improve is a skill published in the GitHub repository agno-agi/agentos-render (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,337 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 98% identical to review-and-improve, differing in 2 lines, and is treated as a copy.