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 instructions/v3velev/memorythreads/claude-mdgit clone --depth 1 https://github.com/v3velev/memorythreadsWhat 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 | $0.00614 | $0.00614 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
memorythreads CLAUDE.md 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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Server - Development Rules
Schema
- The live schema is defined by
ensureCanonicalSchema()inmemory-schema.jsand created automatically on first server/worker start. Update it there, and keepSCHEMA.mdin sync. - SQLite cannot ALTER a CHECK constraint - rebuild the table (rename old, create new, copy, drop old) with
PRAGMA foreign_keys = OFFaround it. - After a schema change: verify with
PRAGMA table_info, test INSERTs, and test FTS queries.
Schema Changes / Migrations
- There is no auto-run migration system;
ensureCanonicalSchema()is the source of truth. Any one-off data migration should be a standalone.cjsscript (package.json has"type": "module"), run manually, with a DB backup taken first. - FTS content-sync rebuild must happen OUTSIDE the table-rebuild transaction:
INSERT INTO <fts>(<fts>) VALUES('rebuild').
FTS
- Triggers must include ALL columns of the FTS virtual table (content AND tags)
- After virtual table schema changes:
INSERT INTO <fts>(<fts>) VALUES('rebuild')
Project vs ProjectName
projectis always a hash - used as DB keyprojectNameis human-readable - used for semantic search/embeddings- Never embed the project hash for semantic search (garbage similarity scores)
Incremental Sync
incremental-sync.jsruns via launchd WatchPaths (30s throttle) on~/.claude/projects/- Sync state persisted in
data/sync-state.json - Turns inserted with
embed_status='pending'- worker handles embedding - FTS auto-populated by existing
turns_fts_aitrigger on INSERT - Dedup via
INSERT OR IGNOREwithUNIQUE(thread_id, turn_number) - When modifying turn parsing logic, keep
transcript-parser.js,incremental-sync.js, andworker.jsin sync
Canonical MemoryThreads
threads.source_kindidentifiesclaude,codex,snapshot, orunknownthreads.source_session_idstores the native session id for that sourcethreads.canonical_thread_idconnects multiple native source streams to one MemoryThreadactive_memory_threadsstores the selected canonical MemoryThread per app and cwd- Codex Desktop continuation is memory based. It activates a canonical thread, then hooks inject context on each prompt
- Do not make Codex and Claude Code share native session files
- User prompt and compaction hooks must never emit recovery headers without actual recovered content
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.
- yesterday First seen · 42 lines · 614 tokens per session scan A 6df65f9cf5c6
memorythreads CLAUDE.md is an instructions file published in the GitHub repository v3velev/memorythreads (3 stars, last pushed 2mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0031 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.