self-improve

A process for turning feedback about an agent's behavior into a proposed update to the instructions or documents that guide future sessions.

In plain words
What is it for?
Use it after rejecting, correcting, or overriding an agent's approach when the lesson should be preserved in a skill, rules file, or other guidance document.
Why use it?
It helps prevent the same mistake from recurring without changing the guiding rules without approval.

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/eai-org/agent-toolkit/self-improve
Any agent
npx skills add eai-org/agent-toolkit --skill self-improve
Clone the repo
git clone --depth 1 https://github.com/eai-org/agent-toolkit

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,165 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.01165
Opus 5 $0.00036 $0.00583
Sonnet 5 $0.00014 $0.00233
Haiku 4.5 $0.00007 $0.00117

Measured 2d ago against content hash 788957835740, 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.

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.

skills/self-improve/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-improve

Suggest durable improvements to the skill or governing doc that should have steered the agent, so the next session gets it right without being told again — and apply them only after the user approves. The skill proposes; the user stays in control of every change. Three ways in:

  • Manual — the user invokes /self-improve to deliberately improve a skill or doc.
  • Self-triggered — the agent notices it was corrected on something a skill/doc governs (or should). Don't silently correct and move on, but don't derail the task either: note the lesson, finish what the user asked for, and offer to persist it at the next natural breakpoint.
  • Driven by another skill — a caller hands over content that is already durable guidance plus an already-chosen target (scope, form, and path — possibly a new file). It resolved both with the user, so skip steps 1-2 and run only draft + apply.

"Skill/doc" means any standing instruction: a SKILL.md, AGENTS.md/CLAUDE.md, a coding-standards or convention doc, a rules file — anything that guides future agents.

Hard rules

  • Confirm before applying. The skill's job is to suggest, never to change text on its own. Never edit a skill or doc without the user's explicit go-ahead on the concrete change — present it as a diff and apply only on approval, whether the user invoked the skill or the agent self-triggered. State plainly whether a change is not yet applied (awaiting approval) or already applied (and where), so the user never has to ask.
  • Editing any skill/doc → always route the write through one of two skills to keep it compact; never edit it directly. A SKILL.md goes through compact-skill-creator; any other doc (rule, AGENTS.md/CLAUDE.md, convention doc) goes through compact-docs-writer. Actually invoke the skill and follow its workflow before drafting or applying; reading it, applying its principles by hand, or naming it after a direct edit does not count.

Read the full file on GitHub · 74 lines

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 · 74 lines · 71 tokens per session scan A 788957835740

Subscribe to this mod's changes

self-improve is a skill published in the GitHub repository eai-org/agent-toolkit (43 stars, last pushed 12d ago), licensed MIT. It adds 71 tokens to every session and 1,165 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

gsd-audit-milestone

Audit milestone completion against original intent before archiving.

open-gsd/gsd-core · 17 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

conductor-implement

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

gemini-cli-extensions/conductor · 34 tokens

api-design

Design or review an HTTP/REST/GraphQL API for versioning, pagination, error shapes, idempotency, auth, status codes, cache headers, and breaking-change management. Use when asked to "design an API", "shape the endpoints", "design the schema", "add a new endpoint", "review this API", or when building/modifying a public…

open-gsd/gsd-pi · 91 tokens

create-mcp-server

Build, iterate, and evaluate Model Context Protocol (MCP) servers that expose external services as tools an LLM can call. Covers schema/tool design, error handling, pagination, MCP Inspector testing, and an eval set. Use when asked to "build an MCP server", "create an MCP tool", "wrap this API as MCP", "expose X to…

open-gsd/gsd-pi · 90 tokens

dependency-upgrade

Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…

open-gsd/gsd-pi · 90 tokens