Skip to content

specstoryai/getspecstory / workthreads

workthreads

Flagged

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still an open loop, and what was just started. Use when someone asks "what happened this week", "what is still open", "what did the team finish", "give me the weekly rollup", or wants a status report over a .specstory/history corpus.

# Workthreads

_A weekly work-thread rollup from your SpecStory coding histories._

Workthreads reads the `.specstory/history` transcripts your coding agents already
write and answers, at a glance: **what happened this week, what got finished, and
what is still open and needs a next step.** It groups the window's sessions into
**threads of work per project** and labels each one:

- **new** - first activity within the last 7 days
- **open** - unresolved, still active (the "open loops")
- **closed** - latest outcome was success and it has gone quiet (flagged
  **reverted** when a beat ran a rollback command)

A lead can use it for a weekly standup; an individual can use it to re-orient after
time away ("what was I in the middle of?").

## How it clusters (deterministic, no LLM in the engine)

The engine is robust against both failure modes of naive clustering:

- **A session is one line of work** - a long multi-prompt session collapses into one
  thread, not one-thread-per-prompt.
- **Cross-session merge needs >= 2 shared *rare* keys** (a distinct file or symbol;
  ubiquitous files like `package.json` and short abbreviations are ignored) - so a
  single shared utility file or a plain word never bridges unrelated work.
- **Bounded threads** - a hard session cap stops a whole codebase from chaining into
  one mega-thread.

Output is deterministic (stable sort, no wall-clock in the body), so two runs on the
same corpus are byte-identical.

## Install

From a clone of this repo:

```zsh
cd workthreads
./install.sh
```

That bundles the engine and the skill into `~/.agents/skills/workthreads` and
symlinks it into `~/.claude/skills/workthreads`, so `/workthreads` is available from
**any** Claude Code session in **any** project. It is self-contained - it does not
read from any other skill's directory. Re-run `./install.sh` any time to update.

Requirements: Node >= 22.5 (for `node:sqlite`), and the SpecStory CLI capturing
histories into `.specstory/history/`.

## Use

Start a new Claude Code session (skills load at session start), then:

```
/workthreads
```

or just ask in plain English: _"give me the weekly rollup"_, _"what's still open?"_,
_"what did we finish this week?"_. With no arguments it asks three short questions -
**Scope** (which repos), **Window** (how many days, default 7), **Goal** (full rollup
/ just open loops / recently closed / status) - then runs.

The digest groups threads by project under **New / Open / Recently closed**, each
with evidence refs (`path:line`), last-activity date, and a one-line rationale. It is
also saved to a dated file (`.specstory/workthreads/<YYYY>-W<week>.md`) so rollups are
durable and diffable week over week.

Sample shape:

```
workthreads digest - 31 thread(s) across 3 active project(s) (window: last 7 days)

## marketing
  New
    - run the first-cut skill on the maker video  [new]  · last 2026-06-19 · 1 session, 20 beats
  Open
    - resend contact-topic sync still failing  [open]  · last 2026-06-20 · 2 sessions, 7 beats
  Recently closed
    - extract survey emails for non-solo respondents  [closed]  · last 2026-06-18 · 1 session, 6 beats
```

## Develop

The engine is plain Node (ESM, zero dependencies, `node:sqlite`). Run the tests:

```zsh
cd workthreads
npm test
```

## License

Apache-2.0.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall