code-self-improving-agent-review

code-self-improving-agent-review is a skill for Claude Code, Codex from aidi1723/safe-agent-skills. It costs 33 tokens per session (361 once invoked), scanned A, a copy of business-competitive-teardown-review, Apache-2.0.

A review checklist for deciding whether a proposed self-improving-agent skill should be added, merged, kept as reference material, or rejected. A self-improving agent is software intended to learn from its work or change its own guidance over time.

In plain words
What is it for?
Reviewing a metadata-only self-improvement skill before catalogue inclusion and producing adoption, authoring, and verification guidance.
Why use it?
It helps assess the proposal without running untrusted instructions or treating them as approved. It also checks for duplicate guidance, source ownership, licensing, permissions, and connector assumptions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing a metadata-only self-improvement skill before catalogue inclusion and producing adoption, authoring, and verification guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aidi1723/safe-agent-skills/code-self-improving-agent-review
Install

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.

Any agent
npx skills add aidi1723/safe-agent-skills --skill code-self-improving-agent-review
Clone the repo
git clone --depth 1 https://github.com/aidi1723/safe-agent-skills

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 code-self-improving-agent-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review/github.svg)](https://agentmods.dev/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review)
Your own site
<a href="https://agentmods.dev/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review"><img src="https://agentmods.dev/badge/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review/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 code-self-improving-agent-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review"><img src="https://agentmods.dev/badge/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 75% 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 $0.00033 $0.00361
Opus 5 $0.00016 $0.00180
Sonnet 5 $0.00007 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 9d ago against content hash 4e285f01711f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-self-improving-agent-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 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.

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.

Origin

This is a copy

75% identical to business-competitive-teardown-review — 20 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.

batches/batch-022-claude-skills-bulk-draft/code-self-improving-agent-review/SKILL.md · 51 lines

What it actually says

Self Improving Agent Review

When To Use

Use this draft when reviewing the self-improving-agent metadata-only candidate from claude-skills before deciding whether to author a local OneCode skill, merge it into an existing skill, or keep it reference-only.

Safe Workflow

  1. Identify the task, audience, owner, source domain, target catalog category, and expected artifact.
  2. Compare the candidate with existing trusted Safe-Agent-Skills to avoid duplicate or overlapping guidance.
  3. Draft local OneCode guidance from project requirements and operator review; do not copy upstream skill bodies.
  4. Check provenance, license notes, runtime permissions, and connector assumptions before import.
  5. Produce an adoption recommendation only; Do not execute upstream content or mark this draft trusted.

Expected Output

  • metadata-only candidate summary
  • overlap and merge recommendation
  • local authoring notes
  • required verifier checklist
  • adoption decision: convert, merge, keep reference-only, or reject

Verifier Expectations

  • metadata-only boundary check
  • duplicate skill check
  • provenance and license check
  • import, serial approval, schema-check, maintain-check, and verify before trust

Draft Metadata

  • upstream candidate: self-improving-agent
  • source domain: engineering-team
  • source path: engineering-team/self-improving-agent/skills/self-improving-agent
  • mapped category: code
  • score: 47
  • priority: P3
  • adoption before draft: reference_only
Files

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.

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 · 51 lines · 33 tokens per session scan A 4e285f01711f

Subscribe to this mod's changes

code-self-improving-agent-review is a skill published in the GitHub repository aidi1723/safe-agent-skills (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 33 tokens to every session and 361 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 75% identical to business-competitive-teardown-review, differing in 20 lines, and is treated as a copy.