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.
npx skills add kxdds/sdd-tdd --skill openspec-superpowersgit clone --depth 1 https://github.com/kxdds/sdd-tddWrote 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.
[](https://agentmods.dev/skills/kxdds/sdd-tdd/openspec-superpowers)<a href="https://agentmods.dev/skills/kxdds/sdd-tdd/openspec-superpowers"><img src="https://agentmods.dev/badge/skills/kxdds/sdd-tdd/openspec-superpowers/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.
<a href="https://agentmods.dev/skills/kxdds/sdd-tdd/openspec-superpowers"><img src="https://agentmods.dev/badge/skills/kxdds/sdd-tdd/openspec-superpowers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00045 | $0.01801 |
| Opus 5.5 | $0.00018 | $0.00720 |
| Sonnet 5.5 | $0.00009 | $0.00360 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
openspec-superpowers 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec <-> Superpowers Bridge
This skill orchestrates the SDD-TDD workflow by connecting OpenSpec's artifact pipeline to Superpowers' execution skills. It supports four modes: plan, run, verify, and archive.
Mode: plan
Purpose: Create implementation-plan.md from the sdd-tdd schema template.
Skill dependency: superpowers:writing-plans
Instructions
- Read the current change's
tasks.mdviaopenspec instructions implementation-plan --change <change>. - Activate the
superpowers:writing-plansskill. - Investigate the codebase before writing anything. Read the modules the change touches, confirm build/test/lint commands, note conventions (naming, base classes, route prefixes, DTO patterns) and missing prerequisites (dependencies, config). Record these under "Key facts for implementers" in the plan. A plan written without reading the code is fiction.
- Generate
implementation-plan.mdin the change directory, following the schema template structure exactly -- including its embedded generation rules. - Map every unchecked OpenSpec task ID from
tasks.mdto exactly one plan step. If any task is unmapped, the plan is incomplete -- do not proceed. - Do NOT check off
tasks.mdcheckboxes during planning. Task completion happens only inrunmode.
Quality bar (from superpowers:writing-plans)
The plan must be executable by an engineer with zero context for this codebase who cannot ask questions. Concretely, every step contains:
- Complete, copy-pasteable code -- the actual test and the actual implementation, with imports. Never a description of code.
- Exact file paths from the repo root, marked (create) or (modify).
- Exact commands with expected output -- the RED command with the exact expected failure (assertion message or error type), the GREEN command expecting pass, and a commit command.
Anti-patterns that mean the step must be rewritten, not patched:
- Prose standing in for code: "add validation logic", "wire up the controller", "handle the error case"
- Placeholders:
// TODO,// implement here,..., "similar to Step N" - Commands without expected outcomes: "run the tests" with no stated failure/pass criteria
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.
- 1mo ago First seen · 165 lines · 45 tokens per session scan A 61f03363283a
openspec-superpowers is a skill published in the GitHub repository kxdds/sdd-tdd (1 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,801 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
tdd-test-engineer
Use for test-first development, regression tests, flaky test debugging, coverage gaps, test strategy, CI failures, or converting bugs into minimal reproducible tests.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.