compound-engineering

compound-engineering is a skill for Claude Code, Codex from danstrem2/clawdbot-skill-master-pack. It costs 43 tokens per session (1,651 once invoked), scanned A, original, no licence file.

A system for reviewing an AI agent’s work sessions, saving useful lessons, and updating its memory over time. It can also set up nightly reviews so those lessons are collected regularly.

In plain words
What is it for?
Use it to review sessions, extract lessons, update memory files, and create recurring learning reviews for an agent.
Why use it?
It reduces the need to repeat the same corrections by carrying useful knowledge from earlier sessions into later ones.

Skill for Claude CodeCodex

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

Good fit Use it to review sessions, extract lessons, update memory files, and create recurring learning reviews for an agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danstrem2/clawdbot-skill-master-pack/ai-compound
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 danstrem2/clawdbot-skill-master-pack --skill ai-compound
Clone the repo
git clone --depth 1 https://github.com/danstrem2/clawdbot-skill-master-pack

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 compound-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/danstrem2/clawdbot-skill-master-pack/ai-compound/github.svg)](https://agentmods.dev/skills/danstrem2/clawdbot-skill-master-pack/ai-compound)
Your own site
<a href="https://agentmods.dev/skills/danstrem2/clawdbot-skill-master-pack/ai-compound"><img src="https://agentmods.dev/badge/skills/danstrem2/clawdbot-skill-master-pack/ai-compound/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 compound-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/danstrem2/clawdbot-skill-master-pack/ai-compound"><img src="https://agentmods.dev/badge/skills/danstrem2/clawdbot-skill-master-pack/ai-compound.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,651 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 $0.00043 $0.01651
Opus 5 $0.00022 $0.00826
Sonnet 5 $0.00009 $0.00330
Haiku 4.5 $0.00004 $0.00165

Measured 9d ago against content hash 56cea8349a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compound-engineering 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 9d 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/ai-compound/SKILL.md · 257 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

1 file 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. 9d ago First seen · 257 lines · 43 tokens per session scan A 56cea8349a71

Subscribe to this mod's changes

compound-engineering is a skill published in the GitHub repository danstrem2/clawdbot-skill-master-pack (2 stars, last pushed 7mo ago), with no licence file. It adds 43 tokens to every session and 1,651 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 2026-08-31.

Related

Other skills, from other repositories

gossipcat

Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.

gossipcat-ai/gossipcat-ai · 50 tokens

openclaw-memory-docs

OpenClaw plugin for documentation-grade memory: explicit capture + local searchable store with safe redaction.

davidtoby/agent-skills · 27 tokens

swift-review

Reviews Swift/Xcode codebases, pull requests, local changes, or individual files against Swift best practices including Google's Swift Style Guide, Apple's API Design Guidelines, build performance, memory management, and testing standards. Use this skill whenever the user asks to review Swift code, audit a Swift PR…

bastos/skills · 129 tokens

unhobble-agent-context

Audits and designs lean, coherent context across system prompts, persistent instructions, repository guidance, skills, tool descriptions, memory, and references. Use for context engineering; creating, reviewing, simplifying, or reorganizing agent context; resolving conflicting, duplicated, bloated, stale, or misplaced…

bastos/skills · 77 tokens

session-logs

Search and analyze your own session logs (older/parent conversations) using jq.

davidtoby/agent-skills · 20 tokens

proactive-agent

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.

davidtoby/agent-skills · 46 tokens