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 aidi1723/safe-agent-skills --skill code-self-improving-agent-reviewgit clone --depth 1 https://github.com/aidi1723/safe-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/skills/aidi1723/safe-agent-skills/code-self-improving-agent-review)<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.
<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>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 | $0.00033 | $0.00361 |
| Opus 5 | $0.00016 | $0.00180 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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.
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.
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
- Identify the task, audience, owner, source domain, target catalog category, and expected artifact.
- Compare the candidate with existing trusted Safe-Agent-Skills to avoid duplicate or overlapping guidance.
- Draft local OneCode guidance from project requirements and operator review; do not copy upstream skill bodies.
- Check provenance, license notes, runtime permissions, and connector assumptions before import.
- 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
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.
- 9d ago First seen · 51 lines · 33 tokens per session scan A 4e285f01711f
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…