understand-agent

understand-agent is a skill for Claude Code, Codex from future-agi/agent-learning-kit. It costs 22 tokens per session (3,489 once invoked), scanned A, original, no licence file.

A source-reading guide for an AI agent, meaning a software system that can take actions or answer requests. It records only claims about the agent that can be checked in its source code.

In plain words
What is it for?
It helps document an agent’s behavior, limits, and implementation for later testing or review.
Why use it?
Agent behavior can be easy to misunderstand when it is described informally. This provides a factual description based on what the code actually shows.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit It helps document an agent’s behavior, limits, and implementation for later testing or review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/future-agi/agent-learning-kit/understand-agent
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 future-agi/agent-learning-kit --skill understand-agent
Clone the repo
git clone --depth 1 https://github.com/future-agi/agent-learning-kit

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 understand-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/future-agi/agent-learning-kit/understand-agent/github.svg)](https://agentmods.dev/skills/future-agi/agent-learning-kit/understand-agent)
Your own site
<a href="https://agentmods.dev/skills/future-agi/agent-learning-kit/understand-agent"><img src="https://agentmods.dev/badge/skills/future-agi/agent-learning-kit/understand-agent/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 understand-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/future-agi/agent-learning-kit/understand-agent"><img src="https://agentmods.dev/badge/skills/future-agi/agent-learning-kit/understand-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,489 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 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 $0.00022 $0.03489
Opus 5 $0.00011 $0.01744
Sonnet 5 $0.00004 $0.00698
Haiku 4.5 $0.00002 $0.00349

Measured yesterday against content hash e5c3189d8d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

understand-agent 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 yesterday.

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.

src/fi/alk/harness/skills/understand-agent/SKILL.md · 252 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

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. yesterday First seen · 252 lines · 22 tokens per session scan A e5c3189d8d5a

Subscribe to this mod's changes

understand-agent is a skill published in the GitHub repository future-agi/agent-learning-kit (119 stars, last pushed today), with no licence file. It adds 22 tokens to every session and 3,489 once invoked, about $0.0001 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 2026-09-12.