harness-studio

50 mods across 1 repository, 9 stars between them.

ac-adversary

01

harness-studio/harness-studio

Agent Claude Code

Attacks acceptance criteria — testability, completeness, edges, concurrency. Phase-1 gate.

9 2mo ago A 24 tokens original MIT

architect

02

harness-studio/harness-studio

Agent Claude Code

Proposes the stack and technical design, with justification and the simplest alternative considered. Input to the ADR.

9 2mo ago A 23 tokens original MIT

backend-dev

04

harness-studio/harness-studio

Agent Claude Code

Implements the backend slice under the approved spec. Owns backend files. Loads python + fastapi skills.

9 2mo ago A 25 tokens original MIT

frontend-dev

07

harness-studio/harness-studio

Agent Claude Code

Implements the frontend slice under the approved spec. Owns frontend files. Loads the typescript skill.

9 2mo ago A 24 tokens original MIT

janitor

09

harness-studio/harness-studio

Agent Claude Code

Scheduled codebase-health auditor (the discovery heartbeat). Scans for drift/debt/latent bugs and reports deduped findings.

9 2mo ago A 29 tokens original MIT

product-analyst

10

harness-studio/harness-studio

Agent Claude Code

Turns a raw brief/overview into a structured problem statement; with split mode, decomposes it into work items. Separates problem from solution.

9 2mo ago A 34 tokens original MIT

regression-hunter

11

harness-studio/harness-studio

Agent Claude Code

Ensures the change doesn't break what already worked. Runs the full suite, checks callers. P4 checker (always on).

9 2mo ago A 30 tokens original MIT

security-adversary

12

harness-studio/harness-studio

Agent Claude Code

Actively ATTACKS the system — injection, auth abuse, secret leakage. P4 checker; mandatory for API/auth surfaces.

9 2mo ago A 31 tokens original MIT

story-writer

13

harness-studio/harness-studio

Agent Claude Code

Breaks a work item into stories with testable acceptance criteria (Gherkin). Turns "guarantees" into stress tests.

9 2mo ago A 31 tokens original MIT

test-adversary

14

harness-studio/harness-studio

Agent Claude Code

Tries to BREAK the system — concurrency, races, edges, tests that pass for the wrong reason. P4 checker.

9 2mo ago A 30 tokens original MIT

test-author

15

harness-studio/harness-studio

Agent Claude Code

Writes the failing tests (the RED step of TDD) from the locked acceptance criteria, before any implementation exists. Maker of tests only — never writes production code.

9 2mo ago A 36 tokens original MIT

api-conventions

22

harness-studio/harness-studio

Skill Claude CodeCodex

Load when designing, building, or reviewing any HTTP/REST API — response shapes, HTTP status codes, filtering/range semantics, pagination, and error bodies. The blessed contract so every endpoint answers the same recurring questions the same way.

9 2mo ago A 51 tokens original MIT

api-design

23

harness-studio/harness-studio

Skill Claude CodeCodex

Load when designing, building, or reviewing APIs — versioning, auth patterns, rate limiting, idempotency, webhooks, breaking vs non-breaking changes, and long-running operations. Extends api-conventions.

9 2mo ago A 46 tokens original MIT

complexity-guard

24

harness-studio/harness-studio

Skill Claude CodeCodex

Load when designing, building, or reviewing any feature — guards against overengineering, unnecessary abstraction, and speculative generalization. The "do you actually need this?" filter.

9 2mo ago A 39 tokens original MIT