memarium-retro

memarium-retro is a skill for Claude Code from june9593/memarium-plugin. It costs 70 tokens per session (1,870 once invoked), scanned A, original, MIT.

A session-review skill that saves reusable lessons from the current coding task into project memory.

In plain words
What is it for?
Use it after debugging, making architectural decisions, changing code, or solving a non-trivial problem.
Why use it?
It helps preserve useful decisions and discoveries for future sessions.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the memarium plugin — 4 skills, 2 hooks shipped together

Good fit Use it after debugging, making architectural decisions, changing code, or solving a non-trivial problem.

Compare 6 skills from other repositories ↓
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 june9593/memarium-plugin
Claude Code
/plugin install memarium

Made for: Claude Code.

Or install memarium, the plugin that ships this one along with the rest of its 4 skills, 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.

agentmods badge for memarium-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/june9593/memarium-plugin/memarium-retro/github.svg)](https://agentmods.dev/skills/june9593/memarium-plugin/memarium-retro)
Your own site
<a href="https://agentmods.dev/skills/june9593/memarium-plugin/memarium-retro"><img src="https://agentmods.dev/badge/skills/june9593/memarium-plugin/memarium-retro/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 memarium-retro

Your own site · 80×15
<a href="https://agentmods.dev/skills/june9593/memarium-plugin/memarium-retro"><img src="https://agentmods.dev/badge/skills/june9593/memarium-plugin/memarium-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,870 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 $0.00070 $0.01870
Opus 5 $0.00035 $0.00935
Sonnet 5 $0.00014 $0.00374
Haiku 4.5 $0.00007 $0.00187

Measured 2d ago against content hash b7d4446c8ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

memarium-retro 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 2d 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/memarium-retro/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memarium retro — in-session memory capture

After completing a task, distill what you learned into memarium's typed memory so the next session (on this or another device) starts already knowing it. This is the live, proactive path: one insight from the CURRENT conversation, captured now — not the batch /memarium digest (which reads already-synced sessions and writes richer typed memory). Both coexist; dedup keeps them from doubling up.

Resolve the plugin CLI for this shell

VBP="${CLAUDE_PLUGIN_ROOT}/bin/memarium-plugin.js"
[ -n "${CLAUDE_PLUGIN_ROOT}" ] && [ -x "$VBP" ] || VBP=$(ls -d ~/.claude/plugins/cache/*/memarium/*/bin/memarium-plugin.js 2>/dev/null | awk -F/ '{print $(NF-2)"\t"$(0)}' | sort -V | tail -1 | cut -f2-)
[ -x "$VBP" ] && "$VBP" --version

The skill loader substitutes ${CLAUDE_PLUGIN_ROOT} with this plugin's installation directory. If that root is unavailable, the fallback selects the highest cached semver, regardless of marketplace name or directory mtime.

Bash calls do not share shell variables. Run discovery and the first CLI command in the same Bash call. For later calls, use the resolved absolute binary path (quoted), or repeat discovery; do not assume $VBP is still set.

If $VBP doesn't resolve, the plugin isn't installed — stop silently (don't block the turn).

Process

digraph retro {
  "Task done" -> "Did I learn something REUSABLE?" [shape=diamond];
  "Did I learn something REUSABLE?" -> "Stop — nothing durable" [label="no"];
  "Did I learn something REUSABLE?" -> "For each insight: pick type + draft" [label="yes"];
  "For each insight: pick type + draft" -> "Fact-hygiene (WHO / WHAT-WHEN / RELATIONSHIP)";
  "Fact-hygiene (WHO / WHAT-WHEN / RELATIONSHIP)" -> "memory-query for existing";
  "memory-query for existing" -> "Covered already?" [shape=diamond];
  "Covered already?" -> "supersede/update (set supersedes:<id>)" [label="yes"];
  "Covered already?" -> "new entry" [label="no"];
  "supersede/update (set supersedes:<id>)" -> "Gated? (core/procedural/pinned/supersede)" [shape=diamond];
  "new entry" -> "Gated? (core/procedural/pinned/supersede)" [shape=diamond];
  "Gated? (core/procedural/pinned/supersede)" -> "memory-propose (queue for review)" [label="yes"];
  "Gated? (core/procedural/pinned/supersede)" -> "memory-write" [label="no"];
}

Read the full file on GitHub · 117 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. 2d ago Changed · +9 lines b7d4446c8ac6
  2. 9d ago First seen · 108 lines · 70 tokens per session scan A 2e6470288af7

Subscribe to this mod's changes

memarium-retro is a skill published in the GitHub repository june9593/memarium-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,870 once invoked, about $0.0003 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

ucai-patterns

Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.

Joncik91/ucai · 42 tokens

memory-curator

Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".

DollarDill/beads-superpowers · 52 tokens

orient

Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…

harnessprotocol/harness-kit · 80 tokens

memory

Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.

harnessprotocol/harness-kit · 76 tokens

capture

Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…

harnessprotocol/harness-kit · 73 tokens

lembas

Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.

justinjdev/fellowship · 51 tokens