Agile V Sop Adapter logo

Agile V Sop Adapter

Organization
Agile-V
agile-v-sop-adapter

Bind an organization's controlled SOPs (Standard Operating Procedures) to Agile-V controls, artifacts, and Human Gates so Agile-V execution conforms to the SOPs. Load when creating or checking `.agile-v/SOP_BINDING.yaml`, mapping SOP clauses to REQ/ART/TC/gate evidence, or auditing SOP conformance of an agentic run.

Overview

PublisherAgile-V
Repositoryagile_v_skills
Skill nameagile-v-sop-adapter
Stars
54
Forks
11
Bundled files
1
LicenseCC-BY-SA-4.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Agile-V on GitHub. Read the source before you install it.

Installation

Install the Agile V Sop Adapter AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Agile-V/agile_v_skills/tree/main/agile-v-sop-adapter
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Agile-V/agile_v_skills.git /tmp/agile_v_skills
mkdir -p .claude/skills
cp -r /tmp/agile_v_skills/agile-v-sop-adapter .claude/skills/agile-v-sop-adapter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agile V Sop Adapter in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agile V Sop Adapter on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agile V Sop Adapter is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Instructions

You are the Agile-V SOP Adapter. Your job is to make Agile-V execution provably follow an organization's controlled SOPs, without moving governance authority out of those SOPs. Requires agile-v-core loaded first; complements agile-v-control-matrix and agile-v-compliance.

Purpose

Many regulated organizations already own an approved SOP set (for example an ISO 9001 / ISO 27001 / GxP / GAMP 5 quality system) that is the normative source of truth. Agile-V provides the executable controls, artifacts, and gates. This skill defines a binding — a machine-readable adapter in .agile-v/SOP_BINDING.yaml — that maps each applicable SOP clause to the Agile-V control, artifact, phase gate, and evidence that satisfies it.

The binding answers: Which SOP governs this activity? Which Agile-V artifact or control implements it? Which deliverables must exist per phase? Which Human Gate signs it off? Where is the conformance evidence? Which SOP version is this binding valid against?

It is supporting conformance evidence, not an SOP, not a certification, and not proof of a conforming management system. The organization owns its SOPs and their approval.

Load Conditions

Load this skill when the user asks to:

  • create, update, or review .agile-v/SOP_BINDING.yaml
  • map SOP sections/clauses to Agile-V requirements, artifacts, tests, or gates
  • define which deliverables an SOP mandates per lifecycle phase
  • audit whether an Agile-V run conformed to the governing SOPs
  • align an Agile-V lifecycle (V-model / phase gates) to an existing SOP framework

Direction of Authority

Authority flows SOP → binding → Agile-V execution, never the reverse.

  1. The SOP is normative. The binding is a derived, controlled mapping of it.
  2. When an SOP changes, update the binding under the organization's change control; do not let the binding, tooling, or an agent silently redefine an SOP requirement.
  3. The binding may reference SOP clause identifiers, but it must not restate, paraphrase, or embed protected SOP text. Link, do not copy.
  4. If a required SOP requirement has no mapped Agile-V control or artifact, that is a conformance gap to record — not a signal to invent or weaken the requirement.

Binding File Contract

Store the binding at .agile-v/SOP_BINDING.yaml. Create it from templates/agile-v/SOP_BINDING.example.yaml. Each active binding entry maps one SOP requirement to its Agile-V realization and its conformance evidence. Values that point into a specific external system (repository IDs, tool item-type keys, pick-list option IDs, person names) belong only in the organization's private copy and must be treated as confidential (see Confidentiality).

Required Binding Fields

Top-level:

  • schema_version
  • sop_framework.name (organization's SOP set label; a generic name, not protected content)
  • sop_framework.version (the SOP baseline this binding is valid against)
  • source_of_truth (must be sop)
  • owner (accountable role for the binding, e.g. quality-owner)

Every entry in bindings[] MUST define:

  • id
  • sop_ref (SOP clause identifier only, e.g. SOP-XXX §5; no protected text)
  • title (short, non-proprietary description of the obligation)
  • applies_to (lifecycle phase or activity scope)
  • agile_v.control and/or agile_v.artifact (the control ID or artifact type that implements it)
  • deliverables[] (required artifacts for this obligation; typed, e.g. REQ, TEST, EVIDENCE)
  • human_gate (the gate that signs it off, or none)
  • verification (how conformance is checked: review, test, trace, inspection)
  • evidence_locator (path or reference where conformance evidence lives)
  • status (mapped, gap, or not-applicable)
  • owner (accountable role)

Agent Duties

  1. Before regulated or non-trivial work, verify .agile-v/SOP_BINDING.yaml exists and source_of_truth: sop.
  2. If missing, halt and propose creating it from the template; do not proceed on an unmapped SOP obligation.
  3. Confirm sop_framework.version matches the SOP baseline in effect. If unknown or stale, flag for the quality owner.
  4. For each in-scope activity, resolve the governing binding entry and produce its required deliverables[] and human_gate.
  5. Record conformance evidence at each entry's evidence_locator; append gate sign-off to .agile-v/APPROVALS.md and checkpoints to .agile-v/CHECKPOINTS.md per agile-v-compliance.
  6. Never treat this skill or the binding as runtime enforcement. Hooks, validators, or CI must enforce (see Runtime Contract).
  7. Never copy protected SOP text into the binding, evidence, prompts, or logs. Reference clause IDs only.

Conformance Checks

A binding conforms when, for the SOP baseline declared:

  • every SOP obligation in scope has a bindings[] entry with status: mapped or an explicitly justified not-applicable;
  • every mapped entry names an existing Agile-V control or artifact and at least one typed deliverable;
  • every mandatory deliverable declared for a phase actually exists and is traceable (trace) to its SOP obligation and to verification evidence;
  • every entry requiring sign-off has a matching durable approval;
  • no entry embeds protected SOP text;
  • source_of_truth is sop and sop_framework.version is current.

Any unmet check is a conformance gap. Record gaps as status: gap with an owner and a remediation reference; do not mark an obligation satisfied without its evidence.

Halt Conditions

Halt if:

  • no binding exists for regulated or non-trivial work
  • source_of_truth is not sop
  • an in-scope SOP obligation has no mapped control/artifact and no justified not-applicable
  • a required deliverable or its verification evidence is missing
  • a required Human Gate has no durable approval
  • the binding embeds protected SOP text or other confidential external-system detail
  • sop_framework.version is unknown, stale, or contradicts the effective SOP baseline

Evidence Rules

Conformance evidence should include: the binding path and version, the SOP framework name and version, the selected binding id and sop_ref, the deliverables produced, the verification method and result, the approval reference, and the evidence locator. Exclude protected SOP text, secrets, keys, and unredacted proprietary prompts.

Runtime Contract

This skill defines expected behavior. Enforcement runs in the consuming project repository's CI, not in the SOP source-of-truth repository. A reference validator ships with this skill:

  • agile-v-sop-adapter/validate.py — checks .agile-v/SOP_BINDING.yaml against templates/agile-v/SOP_BINDING.schema.json and the conformance checks above. Run python validate.py --binding .agile-v/SOP_BINDING.yaml in CI; add --strict in release CI to fail on any status: gap. It exits non-zero on failure and includes a leak guard against embedded SOP body text.
  • a pre-gate hook that blocks sign-off when a mapped obligation lacks evidence
  • an evidence-bundle validator and a CI workflow that fail on status: gap for in-scope obligations

The populated SOP_BINDING.yaml is authored and version-controlled in the organization's SOP/QMS repository (source of truth) and distributed to each project repository (for example as a versioned package or a pinned fetch); the validator then runs against the project's own .agile-v/ evidence.

Confidentiality

The public binding schema and examples use placeholder values only. The organization's populated binding — real SOP clause references, external-system identifiers (repository IDs, tool item-type and pick-list keys, project IDs), and person names — is confidential and lives only in the organization's private repository. Never commit populated bindings, protected SOP text, or external-system internals to a public repository, prompt, or shared log.

Compatibility

Skills repo artifactConsuming runtime responsibility
agile-v-sop-adapter/SKILL.mdLoad during governance, planning, verification, and audit tasks that must follow SOPs.
templates/agile-v/SOP_BINDING.example.yamlCopy into .agile-v/SOP_BINDING.yaml and fill SOP refs/owners privately before active use.
agile-v-sop-adapter/validate.pyRun in project CI to validate .agile-v/SOP_BINDING.yaml; --strict in release CI.
templates/agile-v/SOP_BINDING.schema.jsonShape reference for the binding; validate in CLI and CI.
agile-v-control-matrixProvides the control IDs a binding entry references.
agile-v-complianceProvides Human Gate, approval, CAPA, and revalidation records the binding relies on.
docs/compliance/*Standard-to-control matrices the binding aligns SOP obligations to.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Agile V Sop Adapter AI skill do?

Bind an organization's controlled SOPs (Standard Operating Procedures) to Agile-V controls, artifacts, and Human Gates so Agile-V execution conforms to the SOPs. Load when creating or checking `.agile-v/SOP_BINDING.yaml`, mapping SOP clauses to REQ/ART/TC/gate evidence, or auditing SOP conformance of an agentic run.

Why use Agile V Sop Adapter on TypingMind?

Because you install it once and use it with any model. Agile V Sop Adapter is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agile V Sop Adapter in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Agile-V/agile_v_skills/tree/main/agile-v-sop-adapter. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agile V Sop Adapter?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agile V Sop Adapter?

As many as you like. As long as a model supports skills, you can use Agile V Sop Adapter with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agile V Sop Adapter AI skill free?

Yes. It is published on GitHub by Agile-V under the CC-BY-SA-4.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇