A knowledge-capture skill for recording solutions, project context, lessons, and principles in searchable documents. It can also update CLAUDE.md, a file containing instructions for Claude Code.

Use it after fixing a difficult bug, creating useful agent context, or finding a pattern worth recording for future work.

It preserves hard-won debugging knowledge while the details are still fresh, reducing repeated investigation and conflicting notes.

compound — Skill for Claude Code by ondrej-svec/heart-of-gold-toolkit

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add ondrej-svec/heart-of-gold-toolkit

Claude Code

/plugin install marvin

Made for: Claude Code.

Or install marvin, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks.

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/ondrej-svec/heart-of-gold-toolkit/compound/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/compound)

Your own site

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/compound"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/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/ondrej-svec/heart-of-gold-toolkit/compound"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/compound.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,079 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	$0.00078	$0.02079
Opus 5.5	$0.00031	$0.00832
Sonnet 5.5	$0.00016	$0.00416
Haiku 4.5	$0.00008	$0.00208

Measured 2mo ago against content hash 20153053b88d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

plugins/marvin/skills/compound/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compound

Capture knowledge while context is fresh. Solutions, context docs, learnings — whatever you just discovered, structure it so it's findable and useful next time.

Boundaries

This skill MAY: read code/docs for context, write knowledge documents (solutions, context docs, learnings), update CLAUDE.md. This skill MAY NOT: edit application code, run tests, deploy, fix bugs. Knowledge capture only.

Common Rationalizations

Shortcut	Why It Fails	The Cost
"Skip duplicate check — I'll write a new doc"	Parallel docs drift and eventually contradict	Knowledge drift → wrong fix applied next time
"Skip frontmatter — it's just metadata"	Frontmatter IS the search index. Without it, the solution is unfindable.	Captured but never surfaced → wasted effort
"Good enough — I'll refine later"	You won't. Context is freshest NOW.	Incomplete doc → next person can't reproduce the fix
"Too trivial to document"	The "trivial" fix that took 30 minutes will take someone else 30 minutes too	Repeated debugging of known problems

Phase 0: Detect What to Capture

Entry: User invoked /compound — possibly after a fix, with a topic, or with no context.

Auto-detect capture type:

Context	Capture Type	Output Location
Just fixed a bug, resolved an error	Solution	`docs/solutions/{domain}/{topic}.md`
Need to create/update AI context	Context doc	`CLAUDE.md`, `${CLAUDE_PLUGIN_ROOT}/knowledge/{topic}.md`, or `docs/`
Discovered a pattern or principle	Learning	`CLAUDE.md` or memory files

If invoked after a fix: Scan conversation for what broke, what was investigated, what fixed it. If invoked with a topic (e.g., /compound auth token refresh): Use as hint. If unclear: Use AskUserQuestion with:

question: "What knowledge do you want to capture?"
header: "Type"
options:
1. label: "Solution", description: "Problem → root cause → fix → prevention (for docs/solutions/)"
2. label: "Context doc", description: "AI context, onboarding, or decision record"
3. label: "Learning", description: "Pattern, preference, or principle for CLAUDE.md or memory"
multiSelect: false

Read the full file on GitHub · 235 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.

2mo ago First seen · 235 lines · 78 tokens per session scan A 20153053b88d

Subscribe to this mod's changes

compound is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,079 once invoked, about $0.0003 per session on Opus 5.5. 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.

Memory and context Writing and docs

compound next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
compoundondrej-svec/heart-of-gold-toolkit	Skill	19	1mo ago	MIT	A	78	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	today	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	today	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	0	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex