A documentation workflow that records a recently solved problem or useful project term in Markdown files such as `docs/solutions/` or `CONCEPTS.md`. It adds structured metadata so the notes can be found later.

Use it after fixing a problem or learning a durable concept to create searchable project notes for teammates and future work.

It prevents useful discoveries from being lost in chat, memory, or old code changes. Future work on the same problem can start from the recorded solution instead of repeating the research.

ce-compound — Skill for Claude Code by elleryfamilia

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 elleryfamilia/loadout --skill ce-compound

Clone the repo

git clone --depth 1 https://github.com/elleryfamilia/loadout

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/elleryfamilia/loadout/ce-compound/github.svg)](https://agentmods.dev/skills/elleryfamilia/loadout/ce-compound)

Your own site

<a href="https://agentmods.dev/skills/elleryfamilia/loadout/ce-compound"><img src="https://agentmods.dev/badge/skills/elleryfamilia/loadout/ce-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/elleryfamilia/loadout/ce-compound"><img src="https://agentmods.dev/badge/skills/elleryfamilia/loadout/ce-compound.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 12,161 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.12161
Opus 5	$0.00016	$0.06080
Sonnet 5	$0.00006	$0.02432
Haiku 4.5	$0.00003	$0.01216

Measured yesterday against content hash 5d68a17bf957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ce-compound 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.

vendored/compound-engineering/ce-compound.SKILL.md · 713 lines

How it starts

The opening of the file, as written. The whole thing — 713 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ce-compound

Coordinate multiple subagents working in parallel to document a recently solved problem.

Purpose

Captures problem solutions while context is fresh, creating structured documentation in docs/solutions/ with YAML frontmatter for searchability and future reference. Uses parallel subagents for maximum efficiency.

Why "compound"? Each documented solution compounds your team's knowledge. The first time you solve a problem takes research. Document it, and the next occurrence takes minutes. Knowledge compounds.

Usage

/ce-compound                            # Document the most recent fix
/ce-compound [brief context]            # Provide additional context hint
/ce-compound mode:headless              # Non-interactive run for automations
/ce-compound mode:headless [context]    # Non-interactive run with context hint

CONCEPTS.md bootstrap requests

If invoked specifically to create or bootstrap CONCEPTS.md from scratch rather than to document a solved problem, do not run the normal phases — ce-compound populates CONCEPTS.md only as a side effect of documenting a real learning (it seeds the learning's area, not the whole repo; see Phase 2.4). Repo-wide concept-map creation is ce-compound-refresh's job. Redirect a standalone bootstrap request to ce-compound-refresh (which asks whether to build the concept map or run a refresh cycle), then exit.

Mode Detection

Check $ARGUMENTS for a mode:headless token. Tokens starting with mode: are flags, not context — strip mode:headless from arguments before treating the remainder as the brief context hint.

Mode	When	Behavior
Interactive (default)	No mode token present	Ask Full vs Lightweight, ask about session history (Full only), prompt for Discoverability Check consent, end with "What's next?"
Headless	`mode:headless` in arguments	No blocking questions. Run Full mode without session history. Apply the Discoverability Check edit silently if a gap exists. Skip Phase 3 specialized reviews. End with a structured terminal report — no "What's next?" menu.

Read the full file on GitHub · 713 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.

yesterday First seen · 713 lines · 32 tokens per session scan A 5d68a17bf957

Subscribe to this mod's changes

ce-compound is a skill published in the GitHub repository elleryfamilia/loadout (30 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 12,161 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 2026-09-12.

Memory and context Writing and docs ai-agents claude cli codex context-engineering copilot

learn

Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

automagik-dev/genie · 23 tokens

brief

Brief the user on what they saved in a period — the thread running through it, not a list.

Fergana-Labs/stash · 23 tokens

resurface

Pick a few old saves worth revisiting now, and say why now.

Fergana-Labs/stash · 18 tokens

atomicmemory

Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.

atomicstrata/atomicmemory · 50 tokens

atomicmemory-cli

Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.

atomicstrata/atomicmemory · 26 tokens

reflect

Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

bradygaster/squad · 66 tokens