recursive-agent-improvement AGENTS.md

recursive-agent-improvement AGENTS.md is an instructions file for Codex, OpenCode from H-Ali13381/recursive-agent-improvement. It costs 236 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining the recursive-agent-improvement skill, which helps an agent improve its own working process. They identify the source files, bundled training template, mirrored copy, and validation commands.

In plain words
What is it for?
Editing this skill, synchronizing its root and mirror files, checking that it can be installed, and validating the skill package.
Why use it?
They prevent the published skill and its discovery mirror from becoming inconsistent or containing private or generated material.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

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 instructions/h-ali13381/recursive-agent-improvement/agents-md
Clone the repo
git clone --depth 1 https://github.com/H-Ali13381/recursive-agent-improvement

Made for: Codex, OpenCode.

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 recursive-agent-improvement AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/h-ali13381/recursive-agent-improvement/agents-md.svg)](https://agentmods.dev/instructions/h-ali13381/recursive-agent-improvement/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/h-ali13381/recursive-agent-improvement/agents-md"><img src="https://agentmods.dev/badge/instructions/h-ali13381/recursive-agent-improvement/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 236 This file is loaded in full into every session.
When invoked 236 The same file — it is already loaded in full.
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 5.1 $0.00236 $0.00236
Opus 5 $0.00118 $0.00118
Sonnet 5 $0.00047 $0.00047
Haiku 4.5 $0.00024 $0.00024

Measured 6d ago against content hash fd63f91610f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

recursive-agent-improvement AGENTS.md 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 6d 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.

AGENTS.md · 31 lines

What it actually says

Agent Notes

This repository publishes one Agent Skill: recursive-agent-improvement.

Canonical files:

  • SKILL.md is the source of truth for the skill.
  • assets/pytorch-training-pipeline/ contains the bundled specialist-training template referenced by the skill.
  • .agents/skills/recursive-agent-improvement/ is a cross-client discovery mirror containing the same SKILL.md and bundled assets.

When editing the skill, update the root SKILL.md and assets/ first, then copy them to the mirror path so the discoverable package stays complete.

Related skill:

Installability check:

npx skills add H-Ali13381/recursive-agent-improvement --list

Validation check:

npx skill-tools check .
npx skill-tools check .agents/skills

Do not add private paths, secrets, local debug notes, model weights, generated reports, or session-specific history to this public skill artifact.

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. 6d ago First seen · 31 lines · 236 tokens per session scan A fd63f91610f0

Subscribe to this mod's changes

recursive-agent-improvement AGENTS.md is an instructions file published in the GitHub repository H-Ali13381/recursive-agent-improvement (3 stars, last pushed 3mo ago), licensed MIT. It adds 236 tokens to every session, about $0.0012 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.