sdd-gates

sdd-gates is a skill for Claude Code, Codex from vladm3105/aidoc-flow-framework. It costs 41 tokens per session (421 once invoked), scanned A, original, MIT.

A verification skill for running the required checks on a proposed change. It selects checks based on the parts touched and uses an error catalogue to explain and resolve failures before merging.

In plain words
What is it for?
Use it to run requirements, design, plan, specification, and code checks; record findings; fix their causes; and confirm a clean result.
Why use it?
It prevents changes from being merged while required checks are failing. It also ensures that documentation-only changes are not treated as automatically exempt from structural checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run requirements, design, plan, specification, and code checks; record findings; fix their causes; and confirm a clean result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vladm3105/aidoc-flow-framework/sdd-gates
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-gates
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.

agentmods badge for sdd-gates

README.md
[![agentmods](https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-gates/github.svg)](https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-gates)
Your own site
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-gates"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-gates/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.

agentmods 80×15 button for sdd-gates

Your own site · 80×15
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-gates"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-gates.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 421 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00421
Opus 5.5 $0.00016 $0.00168
Sonnet 5.5 $0.00008 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 19d ago against content hash 45626770e3ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-gates 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-gates/SKILL.md · 38 lines

What it actually says

SDD Gate Runner

Framework skill — routes to framework/layers/09_CHG/gates/ (GATE-01, GATE-03, GATE-06, GATE-08, GATE-CODE, GATE-SPEC), GATE_ERROR_CATALOG.md, and GATE_INTERACTION_DIAGRAM.md. Paths below use <skills-root> = this framework/skills/ directory.

1. Select gates by touch

Run the gates for the layers the change touches, not the whole battery by default: GATE-01 for business/product surface, GATE-03 for requirements and architecture, GATE-06 for design and test, GATE-08 for the IPLAN itself, GATE-CODE for any code or implementation artifact, GATE-SPEC for normative framework/ edits. A skill-only change still runs the structural and conformance gates on its PR — "docs-only" is a scope statement, not a verification waiver.

2. Dispose every finding

Every finding resolves through GATE_ERROR_CATALOG.md: fix the cause in the worktree and re-run to green. Additive findings (index rows, registry entries, pins) resolve directly; semantic findings (logic, policy, contradicted contracts) mean stop and escalate — never route around a red gate with a skip flag or an admin override.

3. Merge only on green

When a required check fails, fix every error from the failed logs, push, and re-watch from the new head — a previous run's green is not this commit's. Stop and report to the human when the same check fails twice after a fix attempt, or when the fix reaches beyond the PR's scope.

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.

  1. 19d ago First seen · 38 lines · 41 tokens per session scan A 45626770e3ce

Subscribe to this mod's changes

sdd-gates 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 421 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.

Related

sdd-gates compared with skills from other repositories

sdd-gates next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdd-gatesvladm3105/aidoc-flow-frameworkSkill175d agoMITA41Claude Code, Codex
autoreviewopenclaw/clawhubSkill9.6ktodayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k9d agoMITA115Claude Code, Codex
revdiff-planumputun/revdiffSkill9572d agoMITA84Claude Code
re0-mergeLilMGenius/paperthinSkill1.4ktodayMITA51Claude Code, Codex
explore-unknownsdzhng/skillsSkill1.5kyesterdayMITA162Claude Code, Codex
asplos-writing-stylebrycewang-stanford/Awesome-Journal-SkillsSkill1.4k1mo agoMITA65Claude Code