agents-config: Skill for Claude Code

.agents/skills/sdlc-regulatory/SKILL.md

sdlc-regulatory is a skill for Claude Code, Codex from daochild/agents-config. It costs 91 tokens per session (6,851 once invoked), scanned A, original, MIT.

A governance framework for AI-assisted software development that defines stages, quality checks, risk limits, change records, responsibility, and compliance references.

In plain words
What is it for?
Use it when running or reviewing work through a structured development process, applying quality gates, classifying risk, or checking compliance controls.
Why use it?
It addresses risks such as unreviewed AI changes, security gaps, architectural drift, missing edge cases, and unclear accountability.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is daochild/agents-config's own configuration. It tells Claude Code and Codex how to work on agents-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to daochild/agents-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/daochild/agents-config/main/.agents/skills/sdlc-regulatory/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/daochild/agents-config

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 sdlc-regulatory

README.md
[![agentmods](https://agentmods.dev/badge/skills/daochild/agents-config/sdlc-regulatory.svg)](https://agentmods.dev/skills/daochild/agents-config/sdlc-regulatory)
Your own site
<a href="https://agentmods.dev/skills/daochild/agents-config/sdlc-regulatory"><img src="https://agentmods.dev/badge/skills/daochild/agents-config/sdlc-regulatory.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,851 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 $0.00091 $0.06851
Opus 5 $0.00046 $0.03426
Sonnet 5 $0.00018 $0.01370
Haiku 4.5 $0.00009 $0.00685

Measured today against content hash 757904a88200, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdlc-regulatory 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 today.

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.

.agents/skills/sdlc-regulatory/SKILL.md · 515 lines

How it starts

The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Driven SDLC Regulatory Framework

AI accelerates execution, SDLC controls correctness, risk, and accountability. Source of truth: this skill. It supersedes and absorbs the deleted SOW.md (AI-Driven Software Development Lifecycle); the SOW §… section labels below are historical provenance from that document, kept to trace each control to its origin.

This skill is the methodology layer consumed by the sdlc-* subagents (BMad-style role agents) and enforced by the sdlc-gates always-on rule. It encodes: stages, quality gates, risk-based autonomy caps, AI vs human responsibility split, change traceability, Definition of Done, key risks, success metrics, and a compliance crosswalk.

Anti-pattern (SOW §Why We Need This)

The failure mode this framework exists to prevent:

Requirement → AI → Code → Merge

That flow has no analysis, no validation, no review, and no accountability. AI-driven development adds risks beyond human mistakes: hallucinations, architectural drift, inconsistent implementations, AI-generated technical debt, missing edge cases, security vulnerabilities, over-engineering, incorrect database changes, AI modifying unrelated components, AI reviewing/validating its own incorrect implementation, and code volume outpacing human review capacity. Every gate below exists to block one or more of these failure modes. If a proposed shortcut skips a gate, it is regressing toward this anti-pattern — refuse it.

AI across the SDLC (SOW §1 — Integrate AI Across the SDLC)

AI must participate in all appropriate engineering stages, not just coding. The 13 SOW activities map as follows.

Linear stages (owned by one BMad role each → one gate)

SOW activity Owner Gate
Requirements analysis sdlc-analyst Requirement
Technical specification sdlc-pm Requirement
Architecture analysis sdlc-architect Architecture
Implementation planning sdlc-sm Architecture
Code generation sdlc-dev Implementation
Test generation sdlc-qa Testing
Code review sdlc-reviewer Code Review
Security analysis sdlc-security Security
Documentation every role (artifact per stage) DoD

Read the full file on GitHub · 515 lines

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. today First seen · 515 lines · 91 tokens per session scan A 757904a88200

Subscribe to this mod's changes

sdlc-regulatory is a skill published in the GitHub repository daochild/agents-config (10 stars, last pushed 21d ago), licensed MIT. It adds 91 tokens to every session and 6,851 once invoked, about $0.0005 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 2026-09-07.

Related

Other skills, from other repositories

dev-flow

Orchestrate an end-to-end product-development workflow built on atomic skills. Reads .workflow/meta.json in a project directory, works out which phase the user is in (idea → PRD → tasks → design → scaffolded → pages → modules → tests → pre-deploy gates → deployed), and delegates to whichever specialist skill owns the…

lukedj78/dev-flow · 163 tokens

prd-from-idea

Turn a raw product idea — a paragraph, a Notion dump, a half-formed thought, or a brief that arrived as a file (.docx, .pdf, .pptx, .xlsx: an RFP, a client deck, a Word spec — converted to Markdown first with anydoc) — into a structured PROJECT.md (high-level brief) and PRD.md (product requirements document) inside a…

lukedj78/dev-flow · 212 tokens

prd-to-tasks

Break down a PRD.md into a concrete, executable tasks.md checklist that a developer or an AI agent can pick up and ship. Reads .workflow/PRD.md (and .workflow/PROJECT.md for context), produces .workflow/tasks.md with one task per checkable bullet, grouped by user story or epic, sized to 2–8 hours each. Output is…

lukedj78/dev-flow · 175 tokens

linear-scrum

Take a dev-flow project into Linear and run it with agile scrum: creates or links the Linear Project, pushes .workflow/tasks.md into estimated, labelled issues, sets up 2-week cycles, then keeps Linear as the source of truth — syncing new tasks up, status and velocity down, planning each sprint to the velocity target.…

lukedj78/dev-flow · 185 tokens

babysit-babysitter-issues

This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.

a5c-ai/babysitter · 69 tokens

agent-coordination

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

a5c-ai/babysitter · 31 tokens