improve-agent

An agent-improvement skill updates an agent’s formula TOML configuration after problems are found during or after a run. It classifies the failure, looks for similar weaknesses, and applies a targeted change.

In plain words
What is it for?
It is for improving formulas after manual intervention, incorrect results, or cleanup work, and for checking related formulas for the same weakness.
Why use it?
It helps turn manual fixes and execution mistakes into improvements that reduce the chance of the same problem recurring.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/stempeck/agentfactory/improve-agent
Any agent
npx skills add stempeck/agentfactory --skill improve-agent
Clone the repo
git clone --depth 1 https://github.com/stempeck/agentfactory

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00067 $0.02535
Opus 5 $0.00034 $0.01267
Sonnet 5 $0.00013 $0.00507
Haiku 4.5 $0.00007 $0.00253

Measured 2d ago against content hash 8945d66e307c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve-agent 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 2d 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.

.claude/skills/improve-agent/SKILL.md · 219 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 219 lines · 67 tokens per session scan A 8945d66e307c

Subscribe to this mod's changes

improve-agent is a skill published in the GitHub repository stempeck/agentfactory (3 stars, last pushed 9d ago), licensed AGPL-3.0. It adds 67 tokens to every session and 2,535 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 2026-08-31.