claudekit: Skill for Claude Code

.claude/skills/skill-improver/SKILL.md

Skill Improver is a skill for Claude Code from Nnnsightnnn/claudekit. It costs 33 tokens per session (5,152 once invoked), scanned B, original, no licence file.

A helper that examines a skill when it fails and updates the skill's definition.

In plain words
What is it for?
It helps maintain skills that should improve after unsuccessful attempts.
Why use it?
It reduces the need to diagnose failed skill behaviour and edit the skill manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is Nnnsightnnn/claudekit's own configuration. It tells Claude Code how to work on claudekit 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 claudekit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nnnsightnnn/claudekit. 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/Nnnsightnnn/claudekit/main/.claude/skills/skill-improver/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Nnnsightnnn/claudekit

Made for: Claude Code.

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 Skill Improver

README.md
[![agentmods](https://agentmods.dev/badge/skills/nnnsightnnn/claudekit/skill-improver.svg)](https://agentmods.dev/skills/nnnsightnnn/claudekit/skill-improver)
Your own site
<a href="https://agentmods.dev/skills/nnnsightnnn/claudekit/skill-improver"><img src="https://agentmods.dev/badge/skills/nnnsightnnn/claudekit/skill-improver.svg" alt="Measured on agentmods" 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 5,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00033 $0.05152
Opus 5 $0.00016 $0.02576
Sonnet 5 $0.00007 $0.01030
Haiku 4.5 $0.00003 $0.00515

Measured 7d ago against content hash 3cf2a1b1aab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

Skill Improver scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep "skill-name" .claude/pain-points/ai-error-history.json
.claude/skills/skill-improver/SKILL.md · 755 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

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. 7d ago First seen · 755 lines · 33 tokens per session scan B 3cf2a1b1aab8

Subscribe to this mod's changes

Skill Improver is a skill published in the GitHub repository Nnnsightnnn/claudekit (2 stars, last pushed 2mo ago), with no licence file. It adds 33 tokens to every session and 5,152 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

repo-reading

How Brownspec reads an existing codebase — the project map, the conventions sample, and the blast radius. Use when another Brownspec skill needs repository facts, or when the user asks what a change touches, who calls a symbol, or what this project's conventions are.

yknnv/brownspec · 57 tokens

lead-project

Autonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation, refactoring, review, and bug-hunting skills. Has broad authority — creates tickets, commits, invokes any skill — and only escalates via andon cord for irreversible actions, public releases…

chrisallenlane/claude-swe-workflows · 82 tokens

implement-project

Full-lifecycle project workflow. Takes batched tickets, implements via /implement-batch, runs smoke tests, then executes a comprehensive quality pipeline (refactor, review-arch, review-test, tidy-docs, review-release). Maximizes autonomy with andon cord escape.

chrisallenlane/claude-swe-workflows · 58 tokens

lead-refactor

Autonomous comprehensive refactoring. Three-phase pipeline — Phase 1 /refactor (tactical, loops internally to convergence) → Phase 2 loop of /review-arch + /implement-batch until architectural findings converge below a severity floor (default HIGH+) → Phase 3 /refactor (catches tactical issues introduced by…

chrisallenlane/claude-swe-workflows · 112 tokens

review-health

First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a reference class, helping the user decide where to engage, where to tread carefully, and where to leave alone. Advisory only — no changes made.

chrisallenlane/claude-swe-workflows · 57 tokens

bug-hunt

Proactive bug-hunting workflow. Assesses codebase risk through complexity, coverage, and structural analysis, then spawns focused investigators that write reproducing tests to validate suspected bugs. Thoroughness over speed. Advisory only — produces findings and proposes tickets; does not implement fixes.

chrisallenlane/claude-swe-workflows · 59 tokens