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 medy-gribkov/arcana --skill spec-driven-devgit clone --depth 1 https://github.com/medy-gribkov/arcanaWrote 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/medy-gribkov/arcana/spec-driven-dev)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/spec-driven-dev"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/spec-driven-dev.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01895 |
| Opus 5 | $0.00017 | $0.00948 |
| Sonnet 5 | $0.00007 | $0.00379 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
spec-driven-dev 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 3d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification-Driven Development
You are a specification architect. Convert vague ideas into precise, testable requirements. Plan before coding. Break work into parallelizable tasks with clear dependencies.
Core Principles
- Specifications drive code, not the reverse. Write the spec first. Code implements the spec.
- Ambiguity is a bug. Every unclear requirement gets a
[NEEDS CLARIFICATION]marker. - Research before design. Investigate unknowns before committing to architecture.
- Test-first ordering. Contracts, then tests, then implementation.
- Parallel by default. Mark independent tasks with
[P]for concurrent execution.
Requirements Specification
BAD - Vague requirements:
## Feature: User Authentication
- Users should be able to log in
- Add social login
- Make it secure
GOOD - Structured spec with acceptance criteria:
## Feature: User Authentication
### User Stories
- As a new user, I can register with email/password so I have an account
- As a returning user, I can log in with email/password so I access my data
- As a user, I can log in with Google OAuth so I skip manual registration
### Acceptance Criteria
1. Registration validates: email format, password >= 12 chars, no reuse of last 5
2. Login rate-limits to 5 attempts per 15 minutes per IP
3. Sessions expire after 24h idle, 7d absolute maximum
4. OAuth callback validates state parameter against CSRF
5. All auth endpoints return consistent error shape: `{ error: string, code: string }`
### Out of Scope
- Apple Sign-In (deferred to v2)
- MFA/2FA (separate spec)
### Open Questions
- [NEEDS CLARIFICATION] Session storage: Redis vs DB-backed?
- [NEEDS CLARIFICATION] Password reset flow: email link vs code?
Planning Workflow
BAD - Jump straight to code:
User: "Add a dashboard"
Dev: *starts writing React components*
# 3 days later: wrong data model, missing API endpoints, no error states
GOOD - Structured planning phases:
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.
- 3d ago First seen · 228 lines · 35 tokens per session scan A 726eff6da696
spec-driven-dev is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,895 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
tdd
TDD with red-green-refactor loop and vertical slices. Triggers: TDD, test-first, red-green-refactor, test driving development.
triage-issue
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.
tdd-workflow
Enforce practical Test-Driven Development for code changes in Go services. Use for new features, bug fixes, refactors, API changes, and new modules. Requires Red-Green-Refactor evidence, defect-hypothesis-driven tests, killer cases, and coverage gates (line + risk-path).
refactor-ops
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…
testing-ops
Cross-language testing strategies and patterns. Triggers on: test pyramid, unit test, integration test, e2e test, TDD, BDD, test coverage, mocking strategy, test doubles, test isolation.