Compare commits

...
Author SHA1 Message Date
Drew RitterandClaude Fable 5 2783fb9145 docs: drop Hermes post-compaction caveat from README install block
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-07 16:50:31 -07:00
Drew RitterandClaude Fable 5 d3f0f13a87 docs: add Hermes Agent to TOC and fix section order
Hermes Agent was in the Quickstart list and had an install section, but
was missing from the Table of Contents and its section sat after Pi,
out of the alphabetical order the other harnesses follow. Section text
moved verbatim.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-07 16:37:51 -07:00
Drew RitterandClaude Fable 5 96c005307e docs: add Qwen Code install instructions to README
Qwen Code installs Claude Code marketplace plugins natively
(qwen extensions install obra/superpowers) and loads the extension's
GEMINI.md context and skills, so no integration work is needed —
only install docs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-07 16:02:02 -07:00
Drew RitterandGitHub 2d4b675b49 Merge pull request #1995 from caiolopes/add-devin-cli-support
feat: add Devin CLI support
2026-08-07 13:42:37 -07:00
Caio LopesandDrew Ritter d21e171f57 Drop devin-tools.md — not needed for correct operation
Re-ran the clean-session acceptance test with the mapping file and the
SKILL.md Platform Adaptation pointer removed: using-superpowers and
brainstorming still auto-trigger first, and the full workflow chain
(writing-plans, executing-plans, TDD, verification) resolves every action
to Devin's native tools. Devin CLI's own system prompt already documents
its tools (skill invocation, subagent profiles, todo tracking, question
prompts), so the mapping was redundant. Test now validates the manifest only.
2026-08-07 12:47:29 -07:00
Caio LopesandDrew Ritter 09a567b6f4 feat: add Devin CLI support
Devin CLI's `devin plugins install obra/superpowers` fails today because the
repo has no `.devin-plugin/plugin.json` manifest. Add the manifest (skills are
auto-discovered from the co-located skills/ directory), a Devin tool mapping
linked from using-superpowers' Platform Adaptation section, a README install
section, version tracking in .version-bump.json, a Codex-sync exclude for the
new dotdir, and a CI-safe test mirroring the kimi/antigravity test style.

Bootstrap rides Devin's native skill surfacing: every installed skill's
name + description is injected into the system prompt at session start with a
standing instruction to invoke matching skills via the native skill tool.
Acceptance test ("Let's make a react todo list") passes in a clean session:
using-superpowers and brainstorming auto-trigger before any code is written.
2026-08-07 12:47:29 -07:00
Drew RitterandGitHub d6a10aba55 Merge pull request #2006 from arimu1/fix/1929-copilot-cli-docs-windows
docs(brainstorming): correct Copilot CLI backgrounding guidance for Windows
2026-08-07 12:39:47 -07:00
Drew RitterandGitHub 8f89e512c3 Merge pull request #1919 from boredcity/docs/add-grok-build-cli-to-readme
Docs/add grok build cli to readme
2026-08-07 12:39:06 -07:00
Georgii PerepechkoandDrew Ritter 28125bf284 docs: add Grok Build CLI to README.md 2026-08-07 12:33:35 -07:00
Drew RitterandGitHub c367f804bb Merge pull request #2063 from obra/fix/t4-brainstorming-three-paths
feat(brainstorming): three-path router — ceremony scales, approval never does
2026-08-06 22:20:58 -07:00
Jesse Vincent 4dc71b10b3 fix(brainstorming): bounded means existing code in this repo, not a familiar app genre
Triggering battery: Claude Code classified a brand-new project bounded
3/3 by reading 'existing, understood flow' as genre familiarity — once
while explicitly noting the repo was empty. Gemini routed the same
prompt architectural 3/3.
2026-07-31 09:39:55 -07:00
Jesse Vincent b68eaf96bb fix(brainstorming): bounded-path approval is a hard stop
Live ceremony battery: bounded reps produced zero doc ritual (the
measured win) but 2/3 implemented before any approval turn; the
bounded path now states the stop explicitly.
2026-07-31 09:39:55 -07:00
Jesse Vincent 6211388f4b feat(brainstorming): three-path router — ceremony scales, approval never does
Spike / bounded / architectural classification said out loud, one-way
upgrade ratchet, approval gate on every path. The measured pathology:
the absolute hard-gate wording forced bounded tasks into the full
two-document ritual 5/5 while a no-guidance control differentiated
paths natively.
2026-07-31 09:39:55 -07:00
arimu1 262ed02103 docs(brainstorming): correct Copilot CLI backgrounding guidance for Windows 2026-07-19 06:15:54 +07:00
7 changed files with 255 additions and 20 deletions
+22
View File
@@ -0,0 +1,22 @@
{
"name": "superpowers",
"version": "6.2.0",
"description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
"author": {
"name": "Jesse Vincent",
"email": "jesse@fsck.com"
},
"homepage": "https://github.com/obra/superpowers",
"repository": "https://github.com/obra/superpowers",
"license": "MIT",
"keywords": [
"brainstorming",
"subagent-driven-development",
"skills",
"planning",
"tdd",
"debugging",
"code-review",
"workflow"
]
}
+1
View File
@@ -5,6 +5,7 @@
{ "path": ".claude-plugin/plugin.json", "field": "version" }, { "path": ".claude-plugin/plugin.json", "field": "version" },
{ "path": ".cursor-plugin/plugin.json", "field": "version" }, { "path": ".cursor-plugin/plugin.json", "field": "version" },
{ "path": ".codex-plugin/plugin.json", "field": "version" }, { "path": ".codex-plugin/plugin.json", "field": "version" },
{ "path": ".devin-plugin/plugin.json", "field": "version" },
{ "path": ".kimi-plugin/plugin.json", "field": "version" }, { "path": ".kimi-plugin/plugin.json", "field": "version" },
{ "path": ".claude-plugin/marketplace.json", "field": "plugins.0.version" }, { "path": ".claude-plugin/marketplace.json", "field": "plugins.0.version" },
{ "path": "gemini-extension.json", "field": "version" } { "path": "gemini-extension.json", "field": "version" }
+55 -7
View File
@@ -13,12 +13,16 @@ Superpowers is a complete software development methodology for your coding agent
- [Codex App](#codex-app) - [Codex App](#codex-app)
- [Codex CLI](#codex-cli) - [Codex CLI](#codex-cli)
- [Cursor](#cursor) - [Cursor](#cursor)
- [Devin CLI](#devin-cli)
- [Factory Droid](#factory-droid) - [Factory Droid](#factory-droid)
- [Gemini CLI](#gemini-cli) - [Gemini CLI](#gemini-cli)
- [GitHub Copilot CLI](#github-copilot-cli) - [GitHub Copilot CLI](#github-copilot-cli)
- [Grok Build CLI](#grok-build-cli)
- [Hermes Agent](#hermes-agent)
- [Kimi Code](#kimi-code) - [Kimi Code](#kimi-code)
- [OpenCode](#opencode) - [OpenCode](#opencode)
- [Pi](#pi) - [Pi](#pi)
- [Qwen Code](#qwen-code)
- [The Basic Workflow](#the-basic-workflow) - [The Basic Workflow](#the-basic-workflow)
- [Community](#community) - [Community](#community)
- [What's Inside](#whats-inside) - [What's Inside](#whats-inside)
@@ -30,7 +34,7 @@ Superpowers is a complete software development methodology for your coding agent
## Quickstart ## Quickstart
Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Hermes Agent](#hermes-agent), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi). Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Devin CLI](#devin-cli), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Grok Build CLI](#grok-build-cli), [Hermes Agent](#hermes-agent), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi), [Qwen Code](#qwen-code).
## How it works ## How it works
@@ -127,6 +131,20 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
- Or search for "superpowers" in the plugin marketplace. - Or search for "superpowers" in the plugin marketplace.
### Devin CLI
- Install the plugin from this repository:
```bash
devin plugins install obra/superpowers
```
- Update to the latest version with:
```bash
devin plugins update superpowers
```
### Factory Droid ### Factory Droid
- Register the marketplace: - Register the marketplace:
@@ -169,6 +187,32 @@ Superpowers is available via the [official Codex plugin marketplace](https://git
copilot plugin install superpowers@superpowers-marketplace copilot plugin install superpowers@superpowers-marketplace
``` ```
### Grok Build CLI
Superpowers is available via the [official Grok plugin marketplace](https://github.com/xai-org/plugin-marketplace).
- Install the plugin from xAI's official marketplace:
```bash
grok plugin install superpowers@xai-official --trust
```
- Or open the marketplace in the TUI, search for Superpowers, and install it:
```text
/marketplace
```
### Hermes Agent
Install Superpowers as a Hermes plugin from this repository:
```bash
hermes plugins install obra/superpowers --enable
```
Restart any active Hermes sessions after installing.
### Kimi Code ### Kimi Code
Superpowers is available in Kimi Code's plugin marketplace. Superpowers is available in Kimi Code's plugin marketplace.
@@ -218,17 +262,21 @@ pi -e /path/to/superpowers
The Pi package loads the Superpowers skills and a small extension that injects the `using-superpowers` bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility `Skill` tool is required. Subagent and task-list tools remain optional Pi companion packages. The Pi package loads the Superpowers skills and a small extension that injects the `using-superpowers` bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility `Skill` tool is required. Subagent and task-list tools remain optional Pi companion packages.
### Hermes Agent ### Qwen Code
Install Superpowers as a Hermes plugin from this repository: Qwen Code installs plugins from Claude Code marketplaces directly.
- Install the plugin from this repository, and pick `superpowers` when prompted:
```bash ```bash
hermes plugins install obra/superpowers --enable qwen extensions install obra/superpowers
``` ```
Restart any active Hermes sessions after installing. Note: Hermes has no - Update later:
post-compaction hook, so a very long session that compacts over its first
turn loses the bootstrap — start a fresh session if skills stop triggering. ```bash
qwen extensions update superpowers
```
## The Basic Workflow ## The Basic Workflow
+1
View File
@@ -48,6 +48,7 @@ EXCLUDES=(
"/.claude-plugin/" "/.claude-plugin/"
"/.codex/" "/.codex/"
"/.cursor-plugin/" "/.cursor-plugin/"
"/.devin-plugin/"
"/.git/" "/.git/"
"/.gitattributes" "/.gitattributes"
"/.github/" "/.github/"
+106 -7
View File
@@ -7,20 +7,91 @@ description: "You MUST use this before any creative work - creating features, bu
Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval. Start by classifying how much process the request needs, then work
through your path: understand the context, refine the idea, present a
design, and get your human partner's approval.
<HARD-GATE> <HARD-GATE>
Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity. Do NOT invoke any implementation skill, write any code, scaffold any
project, or take any implementation action until you have told your
human partner what you intend and they have approved it. This applies
to EVERY task on EVERY path below — the ceremony scales with the task;
the approval gate never does.
</HARD-GATE> </HARD-GATE>
## Anti-Pattern: "This Is Too Simple To Need A Design" ## Three Paths
Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval. Before your first question, classify the request and say the
classification out loud — "this looks bounded, so I'll present a short
design here rather than write a spec" — so your human partner can
override it:
- **Spike** — a feasibility question ("can we...", "is it possible...",
"quick and dirty is fine") whose output is an answer, not code you
keep. Present the question and what you'll try in 2-3 sentences, get
a nod, then find out as cheaply as correctness allows. No design
doc, no spec file. Report findings as a recommendation; anything you
built stays labeled throwaway.
- **Bounded** — a well-scoped change to code that already exists in
this repo: a new flag, a small endpoint, a one-file fix.
Understanding the kind of app is not enough — bounded means the flow
you are changing is already here to read. If there is no existing
flow to change, the task is not bounded. Ask the clarifying
questions that matter, present a short design IN CHAT (a few
sentences to a few short paragraphs), and STOP. Implementation
starts only after your human partner says yes to that design — a
bounded task's approval is as hard a gate as an architectural
one. No spec file, no implementation plan document.
- **Architectural** — new projects, new subsystems, changes that
restructure how components fit together or alter interfaces others
depend on. Follow the full process: questions, approaches, sectioned
design, written spec, then the writing-plans skill.
When in doubt between two paths, take the heavier one. The ratchet is
one-way: hidden complexity discovered mid-task upgrades the path —
stop, say so, and step up. Nothing downgrades mid-task.
## Anti-Pattern: "Too Simple To Need Approval"
Every path ends with your human partner approving your intent before
implementation. A todo list, a single-function utility, a config
change — the design may be two sentences in chat, but you MUST present
it and get approval. "Simple" tasks are where unexamined assumptions
cause the most wasted work. What scales with simplicity is the
artifact, never the approval.
## Red Flags
| Thought | Reality |
|---------|---------|
| "This is too simple to need a design" | Simple means a short design, not no design. Two sentences in chat, then approval. |
| "I'll call it bounded and skip the spec" | Reaching for a label to skip work IS the doubt — take the heavier path. |
| "It's bounded and the design is obvious — I'll start while they read it" | The gate is the approval, not the design's length. Present, then stop until you hear yes. |
| "I understand this kind of app, so it's bounded" | Bounded measures the repo, not your familiarity. A new project has no existing flow — it is architectural. |
| "The spike works, so I'll keep the code" | A spike's output is an answer. Keeping the code is a new request — classify it. |
| "It grew, but I'm almost done — no need to re-classify" | Hidden complexity upgrades the path mid-task. Stop and say so. |
| "They approved the spike, so the follow-up change is approved too" | Each task gets its own classification and its own approval. |
## Checklist ## Checklist
You MUST create a task for each of these items and complete them in order: Classify first, announce the path, then create a task for each item on
your path and complete them in order.
**Spike:**
1. **Explore project context** — enough to frame the probe
2. **Present question + probe plan** — 2-3 sentences
3. **Get approval** — a nod is enough
4. **Investigate** — as cheaply as correctness allows
5. **Report findings** — a recommendation; label anything built as throwaway
**Bounded:**
1. **Explore project context** — check files, docs, recent commits
2. **Ask clarifying questions** — one at a time, the ones that matter
3. **Present short design in chat** — approach, files touched, testing
4. **Get approval** — STOP and wait for an explicit yes; presenting the design and starting in the same breath is skipping the gate
5. **Implement** — proceed with the normal development workflow (TDD applies); no plan document
**Architectural:**
1. **Explore project context** — check files, docs, recent commits 1. **Explore project context** — check files, docs, recent commits
2. **Offer the visual companion just-in-time** — NOT upfront. The first time a question would genuinely be clearer shown than described, offer it then (its own message); on approval its browser tab opens for you. If no visual question ever arises, never offer it. See the Visual Companion section below. 2. **Offer the visual companion just-in-time** — NOT upfront. The first time a question would genuinely be clearer shown than described, offer it then (its own message); on approval its browser tab opens for you. If no visual question ever arises, never offer it. See the Visual Companion section below.
3. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria 3. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
@@ -35,6 +106,13 @@ You MUST create a task for each of these items and complete them in order:
```dot ```dot
digraph brainstorming { digraph brainstorming {
"Classify: spike / bounded / architectural" [shape=diamond];
"Present question + probe (2-3 sentences)" [shape=box];
"Ask clarifying questions (bounded)" [shape=box];
"Present short design in chat" [shape=box];
"Human approves?" [shape=diamond];
"Investigate; report recommendation" [shape=doublecircle];
"Implement via normal workflow (no plan doc)" [shape=doublecircle];
"Explore project context" [shape=box]; "Explore project context" [shape=box];
"Ask clarifying questions" [shape=box]; "Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box]; "Propose 2-3 approaches" [shape=box];
@@ -44,7 +122,17 @@ digraph brainstorming {
"Spec self-review\n(fix inline)" [shape=box]; "Spec self-review\n(fix inline)" [shape=box];
"User reviews spec?" [shape=diamond]; "User reviews spec?" [shape=diamond];
"Invoke writing-plans skill" [shape=doublecircle]; "Invoke writing-plans skill" [shape=doublecircle];
"Hidden complexity? Upgrade path" [shape=box];
"Classify: spike / bounded / architectural" -> "Present question + probe (2-3 sentences)" [label="spike"];
"Classify: spike / bounded / architectural" -> "Ask clarifying questions (bounded)" [label="bounded"];
"Classify: spike / bounded / architectural" -> "Explore project context" [label="architectural"];
"Present question + probe (2-3 sentences)" -> "Human approves?";
"Ask clarifying questions (bounded)" -> "Present short design in chat";
"Present short design in chat" -> "Human approves?";
"Human approves?" -> "Investigate; report recommendation" [label="spike: yes"];
"Human approves?" -> "Implement via normal workflow (no plan doc)" [label="bounded: yes"];
"Hidden complexity? Upgrade path" -> "Classify: spike / bounded / architectural";
"Explore project context" -> "Ask clarifying questions"; "Explore project context" -> "Ask clarifying questions";
"Ask clarifying questions" -> "Propose 2-3 approaches"; "Ask clarifying questions" -> "Propose 2-3 approaches";
"Propose 2-3 approaches" -> "Present design sections"; "Propose 2-3 approaches" -> "Present design sections";
@@ -58,10 +146,21 @@ digraph brainstorming {
} }
``` ```
**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans. **Terminal states are path-bound.** Architectural: the ONLY skill you
invoke after brainstorming is writing-plans — never frontend-design,
mcp-builder, or any other implementation skill. Bounded: after
approval, implementation proceeds directly through the normal
development workflow; no plan document. Spike: the terminal state is a
reported recommendation.
## The Process ## The Process
The subsections below serve the bounded and architectural paths (a
spike stops at "present the probe, get a nod"). Sections from
**Exploring approaches** onward are architectural-path depth — for
bounded work, context plus a few questions plus a short in-chat design
is the whole process.
**Understanding the idea:** **Understanding the idea:**
- Check out the current project state first (files, docs, recent commits) - Check out the current project state first (files, docs, recent commits)
@@ -100,7 +199,7 @@ digraph brainstorming {
- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in. - Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
- Don't propose unrelated refactoring. Stay focused on what serves the current goal. - Don't propose unrelated refactoring. Stay focused on what serves the current goal.
## After the Design ## After the Design (architectural path)
**Documentation:** **Documentation:**
+5 -4
View File
@@ -83,10 +83,11 @@ scripts/start-server.sh --project-dir /path/to/project --open --foreground
**Copilot CLI:** **Copilot CLI:**
```bash ```bash
# Use --foreground and start the server via the bash tool with mode: "async" # Start it with Copilot CLI's non-blocking/background shell mechanism so the
# so the process survives across turns. Capture the returned shellId for # server survives across turns. Keep --foreground so the harness, not the
# read_bash / stop_bash if you need to interact with it later. # script, owns backgrounding. The launcher is a .sh, so invoke it via bash
scripts/start-server.sh --project-dir /path/to/project --open --foreground # (on Windows, call Git Bash's bash.exe from the PowerShell tool).
bash scripts/start-server.sh --project-dir /path/to/project --open --foreground
``` ```
**Other environments:** The server must keep running in the background across conversation turns. If your environment reaps detached processes, use `--foreground` and launch the command with your platform's background execution mechanism. **Other environments:** The server must keep running in the background across conversation turns. If your environment reaps detached processes, use `--foreground` and launch the command with your platform's background execution mechanism.
+63
View File
@@ -0,0 +1,63 @@
#!/usr/bin/env bash
# Validate the Devin CLI integration. `devin plugins install obra/superpowers`
# reads `.devin-plugin/plugin.json` and auto-discovers the co-located `skills/`
# directory; Devin CLI surfaces every installed skill's name + description in
# the system prompt at session start and invokes them via its native `skill`
# tool, and its system prompt already documents its own tools (subagent
# profiles, todo tracking, question prompts), so there is no hook, injector,
# or tool-mapping scaffold to test. What IS Devin-specific is the manifest.
#
# Mirrors tests/kimi/test-plugin-manifest.sh. CI-safe: does not require
# `devin` installed.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
MANIFEST="$REPO_ROOT/.devin-plugin/plugin.json"
fail() { echo "FAIL: $*" >&2; exit 1; }
echo "test-devin-plugin: checking Devin CLI manifest"
# --- Manifest is valid and matches the repo version -------------------------
[ -f "$MANIFEST" ] || fail "manifest missing at $MANIFEST"
python3 - "$MANIFEST" <<'PY'
import json
import sys
from pathlib import Path
manifest_path = Path(sys.argv[1])
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
repo_root = manifest_path.parents[1]
if manifest.get("name") != "superpowers":
raise AssertionError(f"plugin name: expected 'superpowers', got {manifest.get('name')!r}")
package = json.loads((repo_root / "package.json").read_text(encoding="utf-8"))
if manifest.get("version") != package.get("version"):
raise AssertionError(
f"manifest version {manifest.get('version')!r} != package.json version {package.get('version')!r}"
)
# Devin CLI plugins carry skills only (auto-discovered from ./skills/); the
# manifest supports metadata + dependency lists, nothing executable.
unsupported = ["skills", "hooks", "commands", "sessionStart", "contextFileName", "inject"]
present = sorted(field for field in unsupported if field in manifest)
if present:
raise AssertionError("unsupported Devin manifest fields present: " + ", ".join(present))
version_config = json.loads((repo_root / ".version-bump.json").read_text(encoding="utf-8"))
entries = version_config.get("files")
if not isinstance(entries, list) or not any(
entry.get("path") == ".devin-plugin/plugin.json" and entry.get("field") == "version"
for entry in entries
if isinstance(entry, dict)
):
raise AssertionError(".version-bump.json must update .devin-plugin/plugin.json version")
print("Devin plugin manifest looks good")
PY
echo "PASS: Devin CLI plugin valid (manifest)"