ttstack
Note
Fork of Lauren Tan's pstack. This plugin is not upstream.
Install
Add the tt-cursor-plugins marketplace, then enable ttstack.
Pick models and project files
Run [/setup-ttstack](skills/setup-ttstack/SKILL.md). It detects the models you can use and writes a User Rule titled ttstack models on your Cursor account. That rule maps each role to a model. It applies to local Agent and to cloud agents started on the same account. Skills read it; a missing rule or line inherits the parent chat model.
Re-run the skill to change a role. Use inherit-parent or auto to keep a role on the parent chat model.
The same run writes docs/code-host.md and docs/issue-tracker.md in the project you work in, if they are missing, from [skills/tt-mode/references/code-host-template.md](skills/tt-mode/references/code-host-template.md) and [skills/tt-mode/references/issue-tracker-template.md](skills/tt-mode/references/issue-tracker-template.md). It asks which provider to use and offers the recipes this plugin ships: GitHub or Azure DevOps for pull requests; Linear or Azure DevOps for tickets.
GitHub needs gh. Azure DevOps needs the Azure DevOps MCP. Linear needs the Linear MCP. Do not run gh on Azure DevOps. If docs/code-host.md is missing, agents use GitHub and gh. If docs/issue-tracker.md is missing, agents still treat tickets as not frozen chrome, but do not call a tracker MCP.
Ground type-system-discipline
type-system-discipline is language-agnostic. It needs a syntax skill for each typed language you work in. That skill maps the principle onto the language's types: unions, brands, exhaustiveness, parse at the boundary.
This plugin ships two: [typescript-best-practices](skills/typescript-best-practices/SKILL.md) and [csharp-best-practices](skills/csharp-best-practices/SKILL.md). The C# skill also covers designing services so decorators can wrap them, and logging and metrics in those decorators.
If you write another typed language, add a skill in that same shape. Apply the principle first, then the syntax for that language. Use [typescript-best-practices](skills/typescript-best-practices/SKILL.md) as the template.
skills
pick /tt-mode from the / menu before you type your task, so cursor attaches the skill to the message.
[/tt-mode](./skills/tt-mode/SKILL.md) runs most of these for you when a step needs them (how, why, architect, arena, swarm, interrogate, unslop, no-comments, technical-writing, tdd, and the principles). the table below is for when you want one directly:
/how do we cancel runs? do we have an n+1 when we look up every run to cancel?
/interrogate review this pr.
all skills
| skill | use it when |
|---|---|
[/tt-mode](./skills/tt-mode/SKILL.md) | default entry point for any non-trivial task. |
[/in-your-own-words](./skills/in-your-own-words/SKILL.md) | you want the agent to play back your goal and the problem before it starts. |
[/sharpen](./skills/sharpen/SKILL.md) | you want a prompt rewritten deeper, not bigger, before you send it: what a top expert would add, their raw material and methods, and an outside check. hands back the prompt and doesn't do the task. |
[/how](./skills/how/SKILL.md) | you want a walkthrough of how a subsystem works. |
[/why](./skills/why/SKILL.md) | you want to know why something was built this way. discovers available MCPs at run time and queries each evidence category in parallel (source control, issue tracker, long-form docs, real-time chat, infra observability, error tracking, analytics warehouse). |
[/architect](./skills/architect/SKILL.md) | you're about to write code that crosses a function boundary and want the caller's usage, types, and module shape settled first. |
[/arena](./skills/arena/SKILL.md) | you want N parallel attempts at the same thing, then to grab the best parts of each. |
[/swarm](./skills/swarm/SKILL.md) | you want N parallel workers across different slices or races, then one aggregated report. |
[/interrogate](./skills/interrogate/SKILL.md) | you have a diff and want several different models to try to break it, including a strict code-quality lens. |
[/setup-ttstack](./skills/setup-ttstack/SKILL.md) | you want to pick which models ttstack uses per role, or write the project's code-host and issue-tracker files. detects your models and writes a config rule. |
[/reflect](./skills/reflect/SKILL.md) | a long task landed and you want the recipe captured as a skill edit. |
[/correct](./skills/correct/SKILL.md) | you keep correcting agents for the same mistakes. mines history for mistake classes, fixes each at the highest level that works, and keeps a table pairing each rule with what enforces it. |
[/teach](./skills/teach/SKILL.md) | you want to actually understand a change or subsystem, not just have it summarized. runs how + why and weaves one plain explanation, built up diagram by diagram. |
[/tdd](./skills/tdd/SKILL.md) | you're fixing a bug and there's a cheap local test path. write the failing test first, then the fix. |
[/benchmark-checklist](./skills/benchmark-checklist/SKILL.md) | you ran a benchmark or measured a speedup or regression. vets the number before you report or act on it. |
[/no-comments](./skills/no-comments/SKILL.md) | strip comments before review; spawns Comment Sicko, fixes accepted findings, offers encodings for claimed constraints. |
[/deslop](./skills/deslop/SKILL.md) | copied from cursor-team-kit. strip AI slop from the diff before commit. |
[/control-cli](./skills/control-cli/SKILL.md) | copied from cursor-team-kit. drive a local CLI or TUI for proof. |
[/control-ui](./skills/control-ui/SKILL.md) | copied from cursor-team-kit. drive a local browser, IDE, or Electron UI for proof. |
[/typescript-best-practices](./skills/typescript-best-practices/SKILL.md) | you're reading or editing typescript. grounds the type-system-discipline principle in syntax. |
[/csharp-best-practices](./skills/csharp-best-practices/SKILL.md) | you're reading or editing c#. grounds the type-system-discipline principle in syntax, plus decorator-friendly services with logging and metrics in the decorators. |
[/figure-it-out](./skills/figure-it-out/SKILL.md) | no bundled playbook fits. designs a rigorous, auditable playbook for the task. |
[/show-me-your-work](./skills/show-me-your-work/SKILL.md) | you want a reviewable decision trail. logs decisions to a tsv you can commit. |
[/create-verification-skill](./skills/create-verification-skill/SKILL.md) | your project has no scripted way to prove app behavior. generates a project-local verify skill with a feature map, for any language or platform. |
[/maintain-verification-skill](./skills/maintain-verification-skill/SKILL.md) | your verify skill's feature map has drifted from the app. source wave + one live pass, at most one PR of proven corrections. |
[/verify-this](./skills/verify-this/SKILL.md) | copied from cursor-team-kit. prove a claim with baseline vs treatment evidence. returns VERIFIED, NOT VERIFIED, or INCONCLUSIVE. a UI claim must pass a case matrix, not only the happy path. |
[/unslop](./skills/unslop/SKILL.md) | you're cleaning up writing. removes AI tells. |
[/bro](./skills/bro/SKILL.md) | you want the last reply again in plain words, with no jargon. |
[/technical-writing](./skills/technical-writing/SKILL.md) | layered doc standard (Diátaxis + Google developer style + STE + Global English) for docs, RFCs, readmes, PR descriptions, commit messages. |
examples
mostly meant to just use [/tt-mode](./skills/tt-mode/SKILL.md) at the start of a task and let it route to a playbook. the other skills fire as the steps need them. a few i reach for directly.
all the examples
| when | example |
|---|---|
| bug fix | /tt-mode this pr has a subtle bug where the scroll drifts every 750ms even when idle. repro first, then fix and verify. |
| perf | /tt-mode a big list takes a second or two to load even though we virtualize. run a cpu trace and tell me why. |
| feature | /tt-mode build a small feature behind a feature flag. verify it really works. |
| prototype | /tt-mode build two prototypes of the markdown renderer so we can compare. spawn an agent for each. |
| multi-phase | /tt-mode open source these skills as a plugin. nothing internal leaks, work in a temp dir, show me the dependency graph first. |
| overnight run | /tt-mode i'm going to bed. land the stack even if ci flakes. i want everything merged by morning. |
| babysit | /tt-mode check on pr 123. anything outstanding? |
| visual parity | /tt-mode the row spacing is too tall when this flag is on. the second image is correct. repro and fix until it matches. |
| figure it out | /tt-mode i'm stepping away. migrate every caller from the synchronous store to the new async one, keeping behavior identical. i want to trust it was done right when i'm back. |
| how | /how do we cancel runs? do we have an n+1 when we look up every run to cancel? |
| why | /why is this feature flag not on yet? |
| architect | design this instrumentation to be high signal with no false positives. /architect this first. |
| arena | /arena take my prompt to the arena verbatim. i want to compare their proposals with yours. |
| swarm | /swarm check every package under packages/ against its check.sh. one worker per package. one report. |
| interrogate | /interrogate review this pr. |
| tdd | /tdd implement |
| unslop | can we unslop and tighten the new changes? |
| reflect | /reflect that took too long. capture what we learned so the next run doesn't repeat it. |
| correct | /correct |
| show-me-your-work | /show-me-your-work keep a decision trail i can review when i'm back. |
| verify-this | /verify-this the list no longer jumps when a row is added. |
the poteto-agent and Comment Sicko subagents
[/tt-mode](./skills/tt-mode/SKILL.md) runs in the chat that receives it. that chat owns the playbook, the todo list, and every subagent spawn.
ttstack also ships [subagent_type: "poteto-agent"](./agents/poteto-agent.md) as the wrapper for delegates spawned during a run. spawn a fresh one for each new task. resume one only in the cases the Subagents section of [/tt-mode](./skills/tt-mode/SKILL.md) names. it reads tt-mode in full, including its inline principles index, before doing any work. substituting generalPurpose skips that read and drifts. do not spawn poteto-agent to run the playbook itself.
ttstack also ships Comment Sicko, a read-only comment reviewer available as subagent_type: "comment-sicko". usually invoke it through [/no-comments](./skills/no-comments/SKILL.md), not directly.
principles
twenty-four short skills, one principle each. tt-mode indexes them inline. Cite a principle only after reading its leaf this session. the standalone files are there so other skills can reference a principle by name, and so the index can point at the full rule for each.
all twenty-four principles
| principle | group | rule |
|---|---|---|
| laziness-protocol | core | Bias toward deletion and the smallest change that solves the problem. |
| foundational-thinking | core | Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious. |
| redesign-from-first-principles | core | Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on. |
| attack-the-premise | core | Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it. |
| subtract-before-you-add | core | Remove dead weight, redundant validators, and stub references first, then build on the simpler base. |
| minimize-reader-load | core | Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope. |
| outcome-oriented-execution | core | Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code. |
| experience-first | core | Choose user delight over implementation convenience; ship fewer polished features over more rough ones. |
| exhaust-the-design-space | core | Build 2-3 competing prototypes and compare side by side before committing. |
| build-the-lever | core | Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun. |
| model-the-domain | architecture | Encode the domain in a structure instead of scattered conditionals. |
| boundary-discipline | architecture | Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions. |
| type-system-discipline | architecture | Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas. |
| make-operations-idempotent | architecture | Converge to the same end state regardless of partial prior runs. |
| migrate-callers-then-delete-legacy-apis | architecture | Migrate callers and delete the old API in the same wave instead of preserving compatibility layers. |
| separate-before-serializing-shared-state | architecture | Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant. |
| prove-it-works | verification | Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, a single happy path, or 'it compiles.'. |
| fix-root-causes | verification | Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate. |
| sequence-verifiable-units | verification | Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer. |
| test-behavior-not-implementation | verification | Apply when you write, change, or keep a test. Assert what the code's users can observe, so the test fails when that behavior breaks and keeps passing when only the internals change. |
| explain-the-number | verification | Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think. |
| guard-the-context-window | delegation | Route bulk to subagents; keep summaries in the main thread, not raw payloads. |
| never-block-on-the-human | delegation | Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions. |
| encode-lessons-in-structure | meta | Encode the rule as a lint, metadata flag, runtime check, or script instead of more text. |