improve-self

improve-self is a skill for Claude Code from sergeyklay/.agents. It costs 211 tokens per session (3,505 once invoked), scanned A, original, Apache-2.0.

A self-improvement helper that looks for recurring gaps in the agent's documented skills after substantial work.

In plain words
What is it for?
Use it to inspect completed work for missing skills, check for duplicates, and draft a candidate SKILL.md for review.
Why use it?
It can reveal when a repeated procedure or improvised recovery process should become a reusable skill, without automatically treating every one-off task that way.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to inspect completed work for missing skills, check for duplicates, and draft a candidate SKILL.md for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergeyklay/.agents/improve-self
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 sergeyklay/.agents --skill improve-self
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

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 improve-self

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeyklay/.agents/improve-self/github.svg)](https://agentmods.dev/skills/sergeyklay/.agents/improve-self)
Your own site
<a href="https://agentmods.dev/skills/sergeyklay/.agents/improve-self"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/improve-self/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 improve-self

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeyklay/.agents/improve-self"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/improve-self.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,505 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 15
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 126
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original 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 $0.00211 $0.03505
Opus 5 $0.00105 $0.01752
Sonnet 5 $0.00042 $0.00701
Haiku 4.5 $0.00021 $0.00350

Measured 5d ago against content hash 46b5ea1d04b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

improve-self 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/discover_skills.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.

.agents/skills/improve-self/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improving Self by Closing Skill Gaps

This skill turns the trace of just-completed work into a question: was there a procedure I should have had written down? When the answer is yes, it scaffolds a candidate Agent Skill into the current project — with the human approving every write.

The discipline is conservative by design. A skill created for a one-off question becomes long-term noise in the activation context of every future task. A skill created without checking existing skills becomes a duplicate and a confusion vector. A skill encoding version-specific or transient behavior becomes a permanent footgun. The bar for creation: a concrete, recurring, procedural gap that survived a check against every existing skill, with the user signing off on the draft.

Running scripts bundled with this skill

Script paths are resolved relative to this SKILL.md, not the agent's CWD. If a relative command (for example python3 scripts/discover_skills.py) fails to resolve, prefix it with the directory the platform loaded SKILL.md from.

Fallback. If python3 is missing or the script cannot be located, every procedure here ships a manual alternative — follow that instead.

What counts as a gap

A gap is procedural and recurring. Not every difficulty is a gap.

Pattern in the trace Skill-shaped?
The agent repeated the same 3-step lookup three times in one task Yes
The agent figured out a non-obvious investigation workflow from scratch and it worked Yes
The agent recovered from an error by inventing a procedure that should be reusable Yes
The user corrected the agent's approach with "no, here we always do X first" Yes
The agent realized mid-task it lacked a playbook other agents would also face Yes
The agent did not know a fact ("what is the Kafka default port?") No — research gap, not skill gap
The agent failed once and recovered easily No — one-off, not recurring
The task was complex but succeeded smoothly No — complexity ≠ missing procedure
The agent had to consult unfamiliar library docs No — that is what research-it is for
The task succeeded without struggle No — nothing to fix

Read the full file on GitHub · 166 lines

Files

What ships with it

4 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. 5d ago Changed · -5 tokens per session 46b5ea1d04b4
  2. 9d ago First seen · 166 lines · 216 tokens per session scan A 9be49185c475

Subscribe to this mod's changes

improve-self is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 211 tokens to every session and 3,505 once invoked, about $0.0011 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