compound-memory

compound-memory is a skill for Claude Code from qGolem/orc. It costs 9 tokens per session (2,081 once invoked), scanned A, original, MIT.

A session-review tool that extracts reusable patterns from the current conversation into memory files. It is intended for meaningful debugging lessons, workarounds, architecture decisions, and integration patterns.

In plain words
What is it for?
Use it at the end of a substantial coding session to review the transcript and save confirmed, reusable lessons as separate memory entries.
Why use it?
It preserves useful knowledge from a completed session without saving trivial or one-time details. It also requires confirmation before writing and avoids overwriting existing memory entries.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the orc plugin — 28 skills, 27 agents shipped together

Good fit Use it at the end of a substantial coding session to review the transcript and save confirmed, reusable lessons as separate memory entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qgolem/orc/compound-memory
View source ↗ qGolem/orc
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 qGolem/orc --skill compound-memory
Clone the repo
git clone --depth 1 https://github.com/qGolem/orc

Made for: Claude Code.

Or install orc, the plugin that ships this one along with the rest of its 28 skills, 27 agents.

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-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/qgolem/orc/compound-memory/github.svg)](https://agentmods.dev/skills/qgolem/orc/compound-memory)
Your own site
<a href="https://agentmods.dev/skills/qgolem/orc/compound-memory"><img src="https://agentmods.dev/badge/skills/qgolem/orc/compound-memory/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-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/qgolem/orc/compound-memory"><img src="https://agentmods.dev/badge/skills/qgolem/orc/compound-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,081 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.02081
Opus 5.5 $0.00004 $0.00832
Sonnet 5.5 $0.00002 $0.00416
Haiku 4.5 $0.00001 $0.00208

Measured 1mo ago against content hash 7af31b12c4ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compound-memory 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 1mo 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/compound-memory/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compound Memory

Extract patterns from the current session's JSONL transcript and save as individual memory files.

Not your role:

  • Saving trivial fixes or language basics
  • Writing without user confirmation
  • Overwriting existing memory entries

When to use:

  • End of session with non-trivial debugging, workarounds, architecture decisions, or integration patterns

What NOT to extract:

  • Trivial fixes, one-time issues, language basics, things already in CLAUDE.md

Process

Step 1: Extract Current Session Transcript

Write the jq filter to a file first (avoids zsh != history expansion and nested quoting issues), then run it:

# Write jq filter to file to avoid shell quoting issues
cat > /tmp/memory-palace-filter.jq << 'JQEOF'
if .type == "user" then
  .message.content |
  if type == "string" then
    "USER: " + .
  elif type == "array" then
    [ .[] |
      if .type == "text" then .text
      elif .type == "tool_result" then
        (.content |
          if type == "string" then .[0:100]
          elif type == "array" then
            [.[] | select(.type == "text") | .text[0:100]] | join(" ")
          else "" end
        ) | if . != "" then "RESULT: " + . else empty end
      else empty end
    ] | map(select(. != "")) | join("\n") |
    if . != "" then "USER:\n" + . else empty end
  else empty end
elif .type == "assistant" then
  [ .message.content // [] | .[] |
    if .type == "text" then .text
    elif .type == "tool_use" then
      "TOOL: " + .name + "(" + (.input | tostring | .[0:100]) + ")"
    else empty end
  ] | map(select(. != "")) | join("\n") |
  if . != "" then "ASSISTANT:\n" + . else empty end
else empty end
JQEOF

Read the full file on GitHub · 247 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.

  1. 1mo ago First seen · 247 lines · 9 tokens per session scan A 7af31b12c4ae

Subscribe to this mod's changes

compound-memory is a skill published in the GitHub repository qGolem/orc (5 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 2,081 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

performance-audit

Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…

greglas75/zuvo · 90 tokens

context-driven-development

Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.

Ibrahim-3d/orchestrator-supaconductor · 40 tokens

knowledge-manager

Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.

Ibrahim-3d/orchestrator-supaconductor · 54 tokens

context-loader

Load project context efficiently for Conductor workflows. Use when starting work on a track, implementing features, or needing project context without consuming excessive tokens.

Ibrahim-3d/orchestrator-supaconductor · 32 tokens

memory

Use before the first memory verb — read or write — whenever the orchestrator is about to touch memory as this turn's subject: deciding what persists, searching, curating, or triaging what a session injected at start.

metraton/gaia · 0 tokens

session-reflection

Use when the user asks to reflect on a session or to compact it -- "reflexionemos sobre la sesión", "cerremos esto", "guardemos lo que aprendimos", "compactemos", "compacta", "let's reflect on this session", "wrap up this session", "compact the session" -- or when closing substantial work: the orchestrator reconciles…

metraton/gaia · 0 tokens