Borrowing it
Nothing to install: this file belongs to AsiaOstrich/EngramGraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AsiaOstrich/EngramGraph/main/.agents/skills/spec-derivation/SKILL.mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote 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/asiaostrich/engramgraph/spec-derivation)<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/spec-derivation"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/spec-derivation/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/asiaostrich/engramgraph/spec-derivation"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/spec-derivation.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 | $0.00130 | $0.01548 |
| Opus 5.5 | $0.00052 | $0.00619 |
| Sonnet 5.5 | $0.00026 | $0.00310 |
| Haiku 4.5 | $0.00013 | $0.00155 |
Grade A, and why
spec-derive 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 14d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forward Derivation | 正向推演
Generate derived artifacts (BDD scenarios, TDD skeletons, ATDD tables) from approved SDD specifications.
從已批准的 SDD 規格生成衍生工件（BDD 場景、TDD 骨架、ATDD 表格）。
Subcommands | 子命令
| Subcommand | Description | Output |
|---|---|---|
all |
Full derivation pipeline (BDD + TDD + IT + E2E + ATDD + Contracts) | .feature + .test.* + .it.test.* + .e2e.test.* + .md + .json |
bdd |
Generate BDD scenarios only | .feature |
tdd |
Generate TDD skeletons only | .test.* |
it |
Generate Integration test skeletons | .it.test.* |
e2e |
Generate E2E test skeletons | .e2e.test.* |
atdd |
Generate ATDD test tables | .md (Markdown tables) |
Workflow | 工作流程
- Read Spec - Analyze the input
SPEC-XXX.mdfile | 分析規格檔案 - Extract AC - Parse all Acceptance Criteria | 解析所有驗收條件
- Generate Artifacts - Create BDD/TDD/ATDD outputs | 產生衍生工件
- Verify - Ensure 1:1 mapping between AC and generated items | 驗證一對一對應
Anti-Hallucination Rules | 防幻覺規則
| Rule | Description | 說明 |
|---|---|---|
| 1:1 Mapping | Every AC has exactly one test/scenario | 每個 AC 對應一個測試 |
| Traceability | All artifacts reference Spec ID and AC ID | 所有工件引用規格與 AC 編號 |
| No Invention | Do not add scenarios not in the spec | 不新增規格外的場景 |
Generated Artifact Tags | 產生工件標籤
| Tag | Meaning | 含義 |
|---|---|---|
[Source] |
Direct content from spec | 直接來自規格 |
[Derived] |
Transformed from source | 從來源轉換 |
[Generated] |
AI-generated structure | AI 產生的結構 |
[TODO] |
Requires human implementation | 需人工實作 |
Usage | 使用方式
/derive all specs/SPEC-001.md - Full derivation pipeline | 完整推演管線
/derive bdd specs/SPEC-001.md - Derive BDD scenarios only | 僅推演 BDD 場景
/derive tdd specs/SPEC-001.md - Derive TDD skeletons only | 僅推演 TDD 骨架
/derive it specs/SPEC-001.md - Derive Integration test skeletons | 推演整合測試骨架
/derive e2e specs/SPEC-001.md - Derive E2E test skeletons | 推演 E2E 測試骨架
/derive atdd specs/SPEC-001.md - Derive ATDD tables | 推演 ATDD 表格
What ships with it
1 file 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.
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.
- 14d ago First seen · 110 lines · 130 tokens per session scan A bc7347f8aebb
spec-derive is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 1,548 once invoked, about $0.0005 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 2026-10-16.
Other skills, from other repositories
testing
Testing: TDD, E2E, preferred patterns, test-value audits, verification, agent testing.
nw-test-design-mandates
Design mandates for acceptance tests - hexagonal boundary, business language abstraction, user journey completeness, pure function extraction, 3 Pillars (domain language / chained narrative / production composition), and the layered ATD discipline (Universe-bound assertion, layer-dependent PBT mode, two-tier…
nw-spike
Runs a timeboxed PROBE to validate one core assumption, then optionally PROMOTES the probe into a walking skeleton — the first e2e thin slice of the feature, committed and demo-able. Use after DISCUSS when the feature involves a new mechanism, performance requirement, or external integration.
nw-ad-critique-dimensions
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof.
nw-bdd-methodology
BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation.
nw-test-organization-conventions
Test directory structure patterns by architecture style, language conventions, naming rules, and fixture placement. Decision tree for selecting test organization strategy.