self-improve

A workflow for finding and implementing the next useful project feature by reviewing documentation, TODOs, recent changes, and gaps in the code.

In plain words
What is it for?
Use it when you want to move a project forward but have not decided what to build next. It asks you to choose a candidate and then implements the selected feature on a separate branch.
Why use it?
It turns scattered plans and unfinished work into a concrete feature choice before implementation begins.

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/ttxs69/coding-agent-eval/self-improve-skill
Any agent
npx skills add ttxs69/coding-agent-eval --skill self-improve-skill
Clone the repo
git clone --depth 1 https://github.com/ttxs69/coding-agent-eval

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,691 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 $0.00099 $0.03691
Opus 5 $0.00049 $0.01845
Sonnet 5 $0.00020 $0.00738
Haiku 4.5 $0.00010 $0.00369

Measured 2d ago against content hash 174a90dd70e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-improve 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/install.sh, tests/test_fixture_project.py, tests/test_static_checks.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

self-improve-skill/SKILL.md · 280 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

5 files 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 · 280 lines · 99 tokens per session scan A 174a90dd70e3

Subscribe to this mod's changes

self-improve is a skill published in the GitHub repository ttxs69/coding-agent-eval (2 stars, last pushed 2mo ago), with no licence file. It adds 99 tokens to every session and 3,691 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

unreal-mcp

Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a .uproject…

44-99/unreal-agent-benchmark · 266 tokens

unreal-game-builder

Use when building, completing, or repairing a playable Unreal Engine game or vertical slice that spans several gameplay, world, presentation, testing, and delivery domains.

44-99/unreal-agent-benchmark · 36 tokens

unreal-ai-navigation

Use when Unreal Engine NPCs need spawning, possession, perception, navigation, patrol, pursuit, attack decisions, Behavior Trees, StateTree, EQS, failure recovery, or proof of a closed AI gameplay loop.

44-99/unreal-agent-benchmark · 48 tokens

unreal-animation

Use when an Unreal Engine character needs an Animation Blueprint, locomotion state machine, blend space, montage, slot, notify, root motion, retargeting, hit reaction, death animation, or animation/runtime synchronization repair.

44-99/unreal-agent-benchmark · 48 tokens

unreal-blueprint-cpp-authoring

Use when an Unreal Engine feature needs a deliberate Blueprint, C++, or hybrid implementation route, especially for reusable state owners, graph changes, modules, components, compile failures, or editor-visible APIs.

44-99/unreal-agent-benchmark · 48 tokens

unreal-combat-systems

Use when an Unreal Engine game needs weapons, attacks, traces, projectiles, damage, health, hit reactions, death, scoring, cooldowns, targeting, combat reset, or recovery from invalid combat events.

44-99/unreal-agent-benchmark · 49 tokens