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/thrialectics/threadlinking/claude-mdgit clone --depth 1 https://github.com/thrialectics/threadlinkingWhat 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 | $0.01349 | $0.01349 |
| Opus 5 | $0.00674 | $0.00674 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
threadlinking 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 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threadlinking
Git tracks what changed. Threadlinking tracks why.
A local-first tool for preserving decision-making context alongside the files you create. When you return to code weeks later, threadlinking tells you the reasoning behind it.
Session Protocol
Starting a Session
- Check existing threads:
threadlinking list - If resuming work: Note the relevant thread name for this session
- For unfamiliar code: Use
threadlinking explain path/to/filebefore modifying
During a Session
- Before modifying significant files:
threadlinking explain path/to/file - When making decisions:
threadlinking snippet THREAD "why we chose X over Y" - When creating files:
threadlinking attach THREAD path/to/file - Finding related context:
threadlinking semantic-search "what you're looking for"
Ending a Session
For significant work sessions, offer to capture what was accomplished:
- Summarize key decisions made
- Save snippets for important reasoning
- Attach any new files to the appropriate thread
Thread Detection
Proactively detect when context should be saved. Look for:
- User mentions a project name ("working on myproject")
- Significant new work spanning multiple files
- Architectural decisions ("let's use PostgreSQL because...")
- User asks to "remember this" or "save this context"
- Design choices that future sessions should know about
- Trade-off discussions ("we could do X or Y, let's go with X because...")
When detected, prompt:
"This looks like context worth preserving. Should I save it to a thread?
I'd suggest 'myproject' - or name it something else."
If a thread might exist: Check threadlinking list first, then ask:
"Should this be part of the existing 'myproject' thread?"
Remember the thread for the session. Once confirmed, use it for all context saves without asking again.
What to Save
Good Snippets (Save These)
- Decisions: "Chose JWT over sessions for stateless API scaling"
- Trade-offs: "Picked PostgreSQL over MongoDB - need ACID for payments"
- Constraints: "Must support offline mode, so local-first architecture"
- Pivots: "Switched from REST to GraphQL after N+1 query issues"
- Architecture: "Event sourcing pattern for audit trail requirements"
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.
- 2d ago First seen · 169 lines · 1,349 tokens per session scan A d0d60518c5d3
threadlinking CLAUDE.md is an instructions file published in the GitHub repository thrialectics/threadlinking (23 stars, last pushed 1mo ago), licensed MIT. It adds 1,349 tokens to every session, about $0.0067 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 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.
vscode buildNext.instructions.md
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
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
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.