A project memory tool that stores short topic summaries as a tree of plain Markdown files in .threadmind. It lets later coding sessions reload the relevant decisions and constraints instead of relying on the entire earlier conversation.

Use it to save decisions, resume topics, start separate work threads, or inspect the project's thread history.

It reduces the need to repeat project context across sessions and keeps summaries reviewable and commit-friendly in Git.

thread-mind — Skill for Claude Code and Codex by mahmoud-nb

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.

Any agent

npx skills add mahmoud-nb/thread-mind-mcp --skill thread-mind

Clone the repo

git clone --depth 1 https://github.com/mahmoud-nb/thread-mind-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mahmoud-nb/thread-mind-mcp/thread-mind/github.svg)](https://agentmods.dev/skills/mahmoud-nb/thread-mind-mcp/thread-mind)

Your own site

<a href="https://agentmods.dev/skills/mahmoud-nb/thread-mind-mcp/thread-mind"><img src="https://agentmods.dev/badge/skills/mahmoud-nb/thread-mind-mcp/thread-mind/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mahmoud-nb/thread-mind-mcp/thread-mind"><img src="https://agentmods.dev/badge/skills/mahmoud-nb/thread-mind-mcp/thread-mind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,323 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.01323
Opus 5.5	$0.00036	$0.00529
Sonnet 5.5	$0.00018	$0.00265
Haiku 4.5	$0.00009	$0.00132

Measured 9d ago against content hash d95e676aebae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

thread-mind 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 9d 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.

skills/thread-mind/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ThreadMind

ThreadMind keeps the context of a project across AI sessions. It stores a tree of threads in the .threadmind/ directory of the project. Each thread holds a short markdown summary of one topic. The context of a thread is its own summary plus the decisions and constraints of its ancestors, so a new session starts from what matters instead of the whole history. Summaries are plain files that a team can commit and review with git.

This skill drives the tools of the ThreadMind MCP server: context_get, summary_update, thread_list and the others listed in references/tools.md.

1. Check that ThreadMind is available

If tools named context_get, summary_update and thread_list are available, go on. Some agents prefix them with the server name, such as mcp__thread-mind__context_get.
If they aren't, the ThreadMind MCP server isn't set up. Tell the user, and show them the configuration for their agent from references/setup.md. Don't edit configuration files or install anything unless the user asks you to.

2. Load the context when a conversation starts

Call context_get once, unless the ThreadMind context is already in the conversation (the Claude Code plugin loads it by itself).
If it reports that there is no ThreadMind project, carry on without ThreadMind, and don't call its tools again unless the user asks. Only create a project (project_create) when the user asks for it.
Treat the Decisions and Constraints of the context as settled: follow them, and point out when a request contradicts one of them.

3. Save what matters as you go

After a decision, a newly found constraint or a completed task, call summary_update with a section, so that only that section changes:

Section	Holds	Update
`decisions`	Choices made, with their reason in a few words	Add to it
`constraints`	What must stay true	Add to it
`state`	Where the work stands	Replace it (`replaceSection: true`)
`open-questions`	What is still undecided	Add or replace
`next-steps`	What to do next	Replace it (`replaceSection: true`)

Read the full file on GitHub · 82 lines

Files

What ships with it

4 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.

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.

9d ago First seen · 82 lines · 0 tokens per session scan A d95e676aebae

Subscribe to this mod's changes

thread-mind is a skill published in the GitHub repository mahmoud-nb/thread-mind-mcp (3 stars, last pushed 9d ago), licensed MIT. It adds 91 tokens to every session and 1,323 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-19.

Git and workflow Memory and context

git-ai-search

Search and restore AI conversation context from git history.

git-ai-project/git-ai · 13 tokens

remember

Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.

pacifio/atlas · 32 tokens

github-ops

GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.

fuyuxiang/echo-agent · 31 tokens

release

Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.

matrixorigin/memoria · 27 tokens

recall-rationale

Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".

tobihagemann/turbo · 74 tokens

release-finalizer

Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.

Fu-Jie/openwebui-extensions · 42 tokens