An evaluation runner that executes the full test-and-evaluation suite and records a PASS or FAIL result for each metric against predefined thresholds.

Use it to verify implemented work, produce an evaluation report, record execution evidence, and identify metrics that still fail.

It replaces informal claims such as “mostly passing” with repeatable, threshold-based results tied to a specific execution record. Failures remain visible and can start a defect-fixing cycle.

sdd-eval — Skill for Claude Code and Codex by vladm3105

Install

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.

Any agent

npx skills add vladm3105/aidoc-flow-framework --skill sdd-eval

Clone the repo

git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-eval/github.svg)](https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-eval)

Your own site

<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-eval"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-eval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-eval"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 338 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.00338
Opus 5.5	$0.00016	$0.00135
Sonnet 5.5	$0.00008	$0.00068
Haiku 4.5	$0.00004	$0.00034

Measured 19d ago against content hash 7fd8f83e9660, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-eval 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 19d 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.

framework/skills/sdd-eval/SKILL.md · 34 lines

What it actually says

SDD EVAL Runner

Framework skill — routes to framework/layers/10_EVAL/EVAL-TEMPLATE.yaml, EVAL-REPORT-TEMPLATE.yaml, and EVAL_WORKFLOW_STANDARD.md. Paths below use <skills-root> = this framework/skills/ directory. Upstream: implemented code plus the sdd-tdd battery; the IPLAN's execution receipt (iplan_receipt_ref) is the evidence anchor.

1. Execute the suites, not a sample

Ingest the evaluation scope, execute the suites, and evaluate each metric against the EVAL strategy's thresholds. Every metric gets a verdict: PASS or FAIL — no partials, no "mostly passing". A verdict must mirror the threshold, not the mood.

2. Report receipts, not stories

Record per-metric verdicts in the EVAL report with the iplan_receipt_ref so the run traces to the exact execution. FAIL verdicts name the broken contract and open the CODE2C loop (defect → IPLAN → code) — they never quietly become known issues.

3. Close out

Deployable fixes close live; static closeout covers the rest. The EVAL report is the audit trail: complete, receipted, and merged before the parent IPLAN is called Verified.

Changes

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.

19d ago First seen · 34 lines · 41 tokens per session scan A 7fd8f83e9660

Subscribe to this mod's changes

sdd-eval is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 338 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 2026-10-26.

Analytics and metrics TDD Testing

sdd-eval next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sdd-evalvladm3105/aidoc-flow-framework	Skill	17	5d ago	MIT	A	41	Claude Code, Codex
engram-testing-coverageGentleman-Programming/engram	Skill	8.2k	today	MIT	A	25	Claude Code, Codex
principle-test-behavior-not-implementationmichael-denyer/pstack-claude	Skill	4.3k	yesterday	MIT	A	50	Claude Code
nw-ddd-eventsourcingnWave-ai/nWave	Skill	635	today	MIT	A	38	Claude Code
nw-leanux-methodologynWave-ai/nWave	Skill	635	today	MIT	A	37	Claude Code
nw-fp-clojurenWave-ai/nWave	Skill	635	today	MIT	A	25	Claude Code
tddcodewithmukesh/dotnet-claude-kit	Skill	833	10d ago	MIT	A	81	Claude Code