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.
npx agentmods add skills/mkupermann/throughline/skillnpx skills add mkupermann/throughline --skill skillgit clone --depth 1 https://github.com/mkupermann/throughlineWrote 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/mkupermann/throughline/skill)<a href="https://agentmods.dev/skills/mkupermann/throughline/skill"><img src="https://agentmods.dev/badge/skills/mkupermann/throughline/skill.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01215 |
| Opus 5 | $0.00041 | $0.00607 |
| Sonnet 5 | $0.00016 | $0.00243 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
claude-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 today.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Memory
Persistent long-term context for Claude Code sessions via a local PostgreSQL DB.
DB connection
Host: localhost:5432
Database: claude_memory
User: $PGUSER (defaults to the current OS user; trust auth, no password)
Python (via psycopg2):
import os, getpass, psycopg2
user = os.environ.get("PGUSER") or getpass.getuser()
conn = psycopg2.connect(host="localhost", port=5432, dbname="claude_memory", user=user)
SQL shell: psql -d claude_memory (use /opt/homebrew/opt/postgresql@16/bin/psql on macOS if $PATH is not set).
Tables
| Table | Purpose | Columns |
|---|---|---|
conversations |
Claude Code sessions | id, session_id, project_name, model, started_at, message_count, summary |
messages |
Individual messages | conversation_id, role, content, tool_name, created_at |
memory_chunks |
Extracted insights | content, category, tags, confidence, project_name |
skills |
Skill metadata | name, description, path, triggers, use_count |
projects |
Project context | name, description, contacts JSONB, decisions JSONB |
prompts |
Reusable templates | name, category, content, tags |
memory_chunks.category enum: decision | pattern | insight | preference | contact | error_solution | project_context | workflow
Workflows
1. Recall ("what do I know about X?")
psql -d claude_memory -c "
SELECT category::text, content, confidence, project_name, created_at
FROM memory_chunks
WHERE content ILIKE '%SEARCH_TERM%'
OR 'SEARCH_TERM' = ANY(tags)
OR project_name ILIKE '%SEARCH_TERM%'
ORDER BY confidence DESC, created_at DESC
LIMIT 20;
"
Use scripts/query.py for structured queries:
python3 ~/.claude/skills/claude-memory/scripts/query.py search "pgvector tuning"
python3 ~/.claude/skills/claude-memory/scripts/query.py project "Project Alpha"
python3 ~/.claude/skills/claude-memory/scripts/query.py contact "Jane Doe"
python3 ~/.claude/skills/claude-memory/scripts/query.py decisions
python3 ~/.claude/skills/claude-memory/scripts/query.py stats
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +2 lines d7e462e7bc84
- 4d ago First seen · 137 lines · 81 tokens per session scan A 22c5957317f7
claude-memory is a skill published in the GitHub repository mkupermann/throughline (21 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,215 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 2026-08-30.
Other skills, from other repositories
remnic-memory-workflow
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end. Trigger phrases include "what do you remember about", "save this for later", "any context from last time".
remnic-recall
Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".
remnic-remember
Store a durable memory in Remnic so every connected agent can recall it. Trigger phrases include "remember this", "save this for later", "add a note that".
remnic-search
Run a deep full-text search across every Remnic memory. Trigger phrases include "search memories for", "find anything about", "deep search".
remnic-status
Check the health of the Remnic daemon, stores, and connected clients. Trigger phrases include "is remnic running", "check memory status", "daemon health".
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.