agentic-self-improvement

agentic-self-improvement is a skill for Claude Code, Codex from ChuckSRQ/awesome-hermes-skills. It costs 41 tokens per session (4,104 once invoked), scanned A, original, MIT.

A feedback loop for testing an agent’s behavior, finding recurring failures, changing its guidance, and checking whether the changes help.

In plain words
What is it for?
Running behavioral benchmarks, diagnosing failure patterns, suggesting or applying guidance patches, verifying changes, optimizing skill text, and creating new benchmarks from session data.
Why use it?
It turns observed mistakes into measured improvements and can undo a change when it causes worse results.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: positional $N argument; mentions Codex; built for hermes-agent.

Good fit Running behavioral benchmarks, diagnosing failure patterns, suggesting or applying guidance patches, verifying changes, optimizing skill text, and creating new benchmarks from session data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chucksrq/awesome-hermes-skills/agentic-self-improvement
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 ChuckSRQ/awesome-hermes-skills --skill agentic-self-improvement
Clone the repo
git clone --depth 1 https://github.com/ChuckSRQ/awesome-hermes-skills

Made for: Claude Code, Codex.

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 agentic-self-improvement

README.md
[![agentmods](https://agentmods.dev/badge/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement/github.svg)](https://agentmods.dev/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement)
Your own site
<a href="https://agentmods.dev/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement"><img src="https://agentmods.dev/badge/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement/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 agentic-self-improvement

Your own site · 80×15
<a href="https://agentmods.dev/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement"><img src="https://agentmods.dev/badge/skills/chucksrq/awesome-hermes-skills/agentic-self-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,104 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.
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 $0.00041 $0.04104
Opus 5 $0.00020 $0.02052
Sonnet 5 $0.00008 $0.00821
Haiku 4.5 $0.00004 $0.00410

Measured 12d ago against content hash b7f620f3eed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agentic-self-improvement 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 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (src/__init__.py, src/apply_and_verify.py, src/benchmark_runner.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.

agentic-self-improvement/SKILL.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Self-Improvement Loop

Behavioral benchmarking + evolutionary self-improvement for Hermes Agent. Combines closed-loop guidance patching (from Hermes PR #6120) with the GEPA optimization framework from hermes-agent-self-evolution (NousResearch, MIT).


Core Loop

BENCHMARK → DIAGNOSE → PATCH → VERIFY → (auto-revert if regression)
                    ↓
              GEPA OPTIMIZE → EVAL DATASET → EVOLVE → DEPLOY
                    ↓
              SESSION MINE → LLM-AS-JUDGE → NEW BENCHMARKS

Two modes operate together:

  • Guidance Patch Loop — fast, surgical, targets specific behavioral failures via guidance blocks
  • Evolutionary Optimization Loop — principled, uses GEPA + DSPy to optimize skill text end-to-end

Part 1: Guidance Patch Loop

Core Loop

BENCHMARK → DIAGNOSE → PATCH → VERIFY → (auto-revert if regression)

Usage

# Run all benchmarks, show suggested patches (no changes made)
/self-improve

# Run all benchmarks, auto-apply if improvement, auto-revert if regression
/self-improve --mode=apply

# Run specific category only
/self-improve --benchmarks=mandatory_tool.yaml

# Run subset of categories
/self-improve --categories=mandatory_tool,act_dont_ask,no_hallucination

# Test a specific model
/self-improve --model=claude-sonnet-4

# Control parallelism (default: 4)
/self-improve --parallel=8

# View past results
/self-improve --view-results=2026-04-12_1400

# Revert last applied patch
/self-improve --revert

Options

Flag Default Description
--mode suggest suggest (show diff only) or apply (apply + verify)
--benchmarks all Benchmark YAML file(s) to run
--categories all Run only specific categories (by filename without .yaml)
--model current Model to benchmark
--parallel 4 Number of parallel prompt executions
--view-results none Show a past run's results
--revert false Revert the last applied patch

Read the full file on GitHub · 449 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. 12d ago First seen · 449 lines · 41 tokens per session scan A b7f620f3eed8

Subscribe to this mod's changes

agentic-self-improvement is a skill published in the GitHub repository ChuckSRQ/awesome-hermes-skills (76 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 4,104 once invoked, about $0.0002 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

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens