threadlink

A command that saves a short explanation or decision to a named project thread and can attach a file.

In plain words
What is it for?
Use it to record why you chose an approach, such as using JWT for authentication, and optionally link the related source file.
Why use it?
It keeps the reasoning behind changes with the project context, so important decisions are easier to find later.

Command

Install

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.

agentmods
npx agentmods add commands/thrialectics/threadlinking/threadlink
Clone the repo
git clone --depth 1 https://github.com/thrialectics/threadlinking
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00302
Opus 5 $0.00007 $0.00151
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured yesterday against content hash 89d7b34d2bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

threadlink 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.

commands/threadlink.md · 46 lines

What it actually says

Save decision context and optionally link a file to a thread.

Usage

/threadlink <thread> "content" [file]

Arguments

  • thread - Thread name (project-level, e.g., "myproject")
  • content - Context to save (focus on the "why")
  • file (optional) - File path to attach to the thread

Examples

/threadlink myproject "Chose JWT for stateless auth"
/threadlink api-v2 "Added rate limiting for security" src/middleware/ratelimit.ts

Instructions

When this command is invoked:

  1. Use the threadlinking_snippet MCP tool to save the content:

    • thread_id: the thread argument
    • content: the quoted content
    • source: "claude-code"
  2. If a file path was provided, also use threadlinking_attach:

    • thread_id: the thread argument
    • file_path: the file path (resolve to absolute if relative)
  3. Confirm what was saved and attached.

Thread Naming

Threads should be project-level, not task-level:

  • Good: myproject, api-v2, client-acme
  • Bad: fix-bug-123, refactor-auth
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. yesterday First seen · 46 lines · 14 tokens per session scan A 89d7b34d2bb8

Subscribe to this mod's changes

threadlink is a command published in the GitHub repository thrialectics/threadlinking (23 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 302 once invoked, about $0.0001 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.