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 magnus919/agent-skills --skill spec-driven-developmentgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/spec-driven-development)<a href="https://agentmods.dev/skills/magnus919/agent-skills/spec-driven-development"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/spec-driven-development/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/magnus919/agent-skills/spec-driven-development"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/spec-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00165 | $0.04092 |
| Opus 5.5 | $0.00066 | $0.01637 |
| Sonnet 5.5 | $0.00033 | $0.00818 |
| Haiku 4.5 | $0.00016 | $0.00409 |
Grade A, and why
spec-driven-development 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 9d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development for AI Software Factories
A methodology for building software where specifications are the executable input to an AI code generation pipeline. The factory model: specs are blueprints, AI agents are the assembly line, verification is quality control, and gates catch defects before they compound.
Pipeline Overview
INCEPTION → [SPECIFY] → REVIEW → [DECOMPOSE] → REVIEW → [IMPLEMENT] → REVIEW → [VERIFY] → DELIVER
↑ ↑ ↑ ↑ ↑ ↑ ↑ ↓
Phase 1 Gate 1 Phase 2 Gate 2 Phase 3 Gate 3 Phase 4 Gate 4
Each phase passes through a gate before the next begins. A defect caught at Gate 1 costs minutes to fix; the same defect found at Gate 4 costs hours.
Use an existing approved PRD, architecture document or issue set as the specification
when it supplies the minimum handoff in references/factory-review-lanes.md.
Throughout this workflow, SPEC.md denotes that authoritative specification; it need
not be a new file or competing copy. Validate equivalent content and traceability.
Run format-specific scripts only when their expected input format applies; otherwise
record the equivalent content checks and any missing information explicitly.
SDD Core Principles
- Make consequential intent explicit. Keep specifications readable and testable. Agents can ask for clarification; unresolved consequential choices need an owner and must stop dependent work before its decision boundary.
- Completeness over brevity. Every missing acceptance criterion is a missing feature. Specifying an edge case upfront costs minutes; discovering it in production costs hours or days.
- Testability over descriptiveness. An AC that cannot produce CLEAR PASS or CLEAR FAIL is not an AC — it's a hope.
- Gates catch defects early. A Gate 1 (spec review) fix costs minutes. A Gate 4 (acceptance review) fix costs hours — the entire implementation may need to be discarded.
- Spec is the single source of truth. Every downstream artifact traces back to the spec. Deviations are defects unless explicitly documented.
- Specs guide test oracles. Gherkin-style ACs can become executable cases, but still need implementation, coverage and oracle review. Independent and withheld scenarios can reveal gaps in visible examples.
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/business-app-rubric-challenges.md 1.5 KB
- evals/evals.json 14 KB
- evals/factory-assurance-challenges.md 2.2 KB
- evals/loan-request.json 90 B
- evals/openai-reference-inputs.json 204 B
- README.md 2.3 KB
- references/ai-factory-pipeline.md 6.1 KB
- references/critiques-and-tradeoffs.md 6.6 KB
- references/example-spec.md 7.8 KB
- references/executable-business-policy.md 4.5 KB
- references/factory-review-lanes.md 5.0 KB
- references/format-translation.md 7.3 KB
- references/methodology-matrix.md 6.5 KB
- references/nfr-encoding.md 5.8 KB
- references/phase-gate-methodology.md 6.0 KB
- references/review-records.md 6.4 KB
- references/sdd-overview.md 4.4 KB
- references/spec-quality-gates.md 5.2 KB
- scripts/business_policy.py 2.3 KB runs code
- scripts/spec-quality-check.sh 2.9 KB runs code
- scripts/spec-to-tasks.sh 2.3 KB runs code
- scripts/test_business_policy.py 2.3 KB runs code
- templates/BUSINESS-POLICY.md 1.5 KB
- templates/FACTORY-REVIEW.md 1.2 KB
- templates/REVIEW.md 3.7 KB
- templates/SPEC.md 3.6 KB
- templates/TASK-PLAN.md 2.5 KB
- templates/VERIFICATION.md 2.7 KB
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.
- 9d ago Changed · +9 lines 6133cd3b755f
- 10d ago Changed · +12 lines 638fea3ef269
- 16d ago Changed · +6 lines d47824d7c663
- 1mo ago First seen · 214 lines · 165 tokens per session scan A 7ec40a49b55d
spec-driven-development is a skill published in the GitHub repository magnus919/agent-skills (149 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 4,092 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
contract
Outcome-driven Cortex function development — declares a behavioral contract before generation begins, enforces evidence-tiered proof before $ship, and defends against the self-oracle evaluation failure mode.
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.