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.
/plugin marketplace add lttr/claude-marketplace/plugin install ccWrote 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.
[](https://agentmods.dev/skills/lttr/claude-marketplace/memory-promote)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/memory-promote"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/memory-promote/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.
<a href="https://agentmods.dev/skills/lttr/claude-marketplace/memory-promote"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/memory-promote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.01369 |
| Opus 5 | $0.00041 | $0.00685 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
memory-promote 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Promote
Auto-memory under <config-dir>/projects/<encoded-cwd>/memory/ is per-conversation context, not durable config. Many memories belong in a more persistent layer where they apply consistently and survive memory pruning. This skill scans memories and proposes a target layer for each.
<config-dir> is $CLAUDE_CONFIG_DIR when set, otherwise ~/.claude. Resolve it once at the start and use it everywhere below.
Scope
The current repo. Memory dirs encode the absolute cwd with / replaced by -:
/home/alex/work/api→<config-dir>/projects/-home-alex-work-api/memory/
Compute MEM_DIR="$CONFIG_DIR/projects/$(pwd | tr / -)/memory". If it doesn't exist, report "no memories for this repo" and stop.
If the user asks for something wider or narrower in their own words — another repo, every project, only the cross-cutting ones, just list them without suggestions — honor it using the same encoding. Don't invent flags for it; the report-then-confirm loop below already gives them control.
Steps
-
List memories.
find "$MEM_DIR" -type f -name '*.md' ! -name 'MEMORY.md'. For each file, read the frontmatter and body. Memory frontmatter looks like:--- name: coolify-deploy description: Deployment coordinates for the app metadata: node_type: memory type: project originSessionId: <uuid> ---The classification key is
metadata.type(commonlyuser,project,feedback,reference). If it is absent, infer the type from the body. -
Classify each memory using the table below.
-
Render report — one row per memory: file, type, current content (1-line summary), → suggested target, rationale, concrete action.
-
Wait for user confirmation before changing anything — promotion is a judgment call, so confirm per-item even when the user asked to just apply everything.
-
On confirm: perform the action (edit CLAUDE.md, invoke
/cc:skill-creator, add the hook tosettings.json, write a reference doc), then delete the memory file and its line inMEMORY.md.
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.
- 11d ago First seen · 88 lines · 82 tokens per session scan A 3ca853a6626a
memory-promote is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,369 once invoked, about $0.0004 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.
Other skills, from other repositories
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you…
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what…
knowledge-spider
A local knowledge-base skill for saving, searching, deleting, and counting records such as preferences, facts, tasks, and other important information.
knowledge
A local knowledge-base connector for searching documents and switching between local retrieval and AnythingLLM, a tool for chatting with documents.
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
forgetful-context-gather
Gather deep context before planning or implementing — one pass that turns a task description into a cited context pack: relevant decisions, patterns, constraints, code pointers, procedures, and explicit gaps. Runs recall from several angles, explores the graph around the strongest hits, and opens the linked material.