context: Skill for Claude Code

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

review-and-improve is a skill for Claude Code, Codex from agno-agi/context. It costs 110 tokens per session (2,840 once invoked), scanned B, original, Apache-2.0.

A repeatable review of a coding project that checks whether its documentation, configuration examples, file paths, scripts, and connected components still agree with the code.

In plain words
What is it for?
Use it to check a repository before sharing or releasing it, keep docs and environment-variable examples current, verify referenced files and scripts, and maintain consistency during ongoing development.
Why use it?
It finds routine documentation and setup drift that can mislead users or break onboarding. It fixes straightforward mismatches and lists issues that need human decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is agno-agi/context's own configuration. It tells Claude Code and Codex how to work on context 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 context configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is _**Coding-agent workflow** — a `/slash-command` your coding agent (Claude Code, Codex, …) runs while developing this repo. Not a runtime skill the deployed @con.

Reuse

Borrowing it

Nothing to install: this file belongs to agno-agi/context. 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/context/main/.agents/skills/review-and-improve/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agno-agi/context

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/context/review-and-improve/github.svg)](https://agentmods.dev/skills/agno-agi/context/review-and-improve)
Your own site
<a href="https://agentmods.dev/skills/agno-agi/context/review-and-improve"><img src="https://agentmods.dev/badge/skills/agno-agi/context/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/context/review-and-improve"><img src="https://agentmods.dev/badge/skills/agno-agi/context/review-and-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,840 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00110 $0.02840
Opus 5 $0.00055 $0.01420
Sonnet 5 $0.00022 $0.00568
Haiku 4.5 $0.00011 $0.00284

Measured 10d ago against content hash 970c0948126d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

review-and-improve scanned grade B with 2 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 10d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- Live container reachable: `curl -sSf http://localhost:8000/health` returns 200. If not, ask the user to `docker compose up -d --build` first — Step 4 needs a live container. (`docker compose ps` is unreliable from work

Makes network callslowCapability

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

- Live container reachable: `curl -sSf http://localhost:8000/health` returns 200. If not, ask the user to `docker compose up -d --build` first — Step 4 needs a live container. (`docker compose ps` is unreliable from work
.agents/skills/review-and-improve/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review and Improve

Coding-agent workflow — a /slash-command your coding agent (Claude Code, Codex, …) runs while developing this repo. Not a runtime skill the deployed @context agent runs; those live in skills/.

You are sweeping the whole repo for public-consumption readiness — docs accuracy, the context agent reachable end to end, scripts that actually do what the docs claim, no stale env vars, format + validate clean. Most drift is mechanical (renamed file, missing entry in example.env, a provider missing from the architecture diagram) and you fix it in place. The rest is a punch list you surface to the user.

This is a recurring sweep — meant to be re-run regularly. On a clean repo it ends with "no diffs"; on a dirty one it brings everything back to coherent.

AGENTS.md is the source of truth for repo conventions; CLAUDE.md is a symlink to it — edit once, both update.

What you auto-fix vs. what you flag

Auto-fix in place (no asking):

  • Stale file paths in any doc.
  • Missing entries in example.env for env vars the code actually reads.
  • Stale entries in example.env for vars nothing reads — delete unless the surrounding comment block describes them as optional/future ("alternate model providers", "future feature"). Flag instead of fixing if intent is unclear.
  • Architecture diagram in AGENTS.md missing a wired provider or runtime skill (or listing one that's gone).
  • An agent file on disk not imported in app/main.py (rare — single-agent product, but the AGENTS.md recipe allows more; add the import + append to agents=[...]).
  • Missing quick_prompts block for a registered agent (draft three from the agent's INSTRUCTIONS; flag the new entries so the user can refine).
  • Missing or wrong cross-links between skill files in .agents/skills/.
  • Single-line factual claim in one doc contradicted by another doc or by code (e.g. one doc says "hot-reload picks up new agents" while another says a restart is required) — auto-fix the doc, not the code.

Read the full file on GitHub · 160 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. 10d ago First seen · 160 lines · 110 tokens per session scan B 970c0948126d

Subscribe to this mod's changes

review-and-improve is a skill published in the GitHub repository agno-agi/context (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,840 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.