Jsp 815 logo

Jsp 815

Community
jgsystemsconsulting
jsp-815

Knowledge pack reconstructed from JSP 815 Defence Safety Management System V1.3 (Ministry of Defence, Open Government Licence v3.0): the SMS Framework, all 12 Elements with their Expectations and Performance Statement themes, and Annexes A to F plus H. Covers the Defence Safety Function and which JSP applies, leadership and safety culture, organisation and SEMS applicability, legislation and exemption certificates, risk assessment and safety cases, supervision and contracting, competence and letters of delegation, equipment and infrastructure safety, performance and incident management, and assurance, audit, and the ISO 45001 clause mapping. SCOPE LIMITS: single-source (JSP 815 V1.3 with Annex H V1.2); carries no DEF-STAN 00-051 or DEF-STAN 00-970 content, no JSP 375, JSP 816; acquisition safety policy is in jsp-376, no Annex G (Assurance Toolkit), and no ISO 45001 text (clause numbers only). This pack is reconstructed reference notes, not MOD guidance, and has no official status.

Overview

Publisherjgsystemsconsulting
Repositoryjgs-se-knowledge-packs
Skill namejsp-815
Stars
121
Forks
1
Bundled files
13
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.

  • 13 bundled files

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

  • Open source

    Published by jgsystemsconsulting on GitHub. Read the source before you install it.

Installation

Install the Jsp 815 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/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/jsp-815
  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/jgsystemsconsulting/jgs-se-knowledge-packs.git /tmp/jgs-se-knowledge-packs
mkdir -p .claude/skills
cp -r /tmp/jgs-se-knowledge-packs/packs/jsp-815 .claude/skills/jsp-815
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jsp 815 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 Jsp 815 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 Jsp 815 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.

JSP 815: Defence Safety Management System (Framework and Direction and Guidance)

When to use

Prerequisites: none: plain Markdown. Familiarity with basic risk vocabulary (hazard, risk, ALARP, assurance) helps; the glossary defines the Defence-specific terms.

Use this skill for questions about how the UK Ministry of Defence manages safety: which JSP answers which need, how a Defence Area structures its safety management arrangements, what the 12 Elements and their Expectations require, when a safety case is needed, how exemption certificates work, how competence and delegation are controlled, how equipment and infrastructure safety is organised, and how assurance and audit are conducted. It is a single-source pack: everything in it derives from JSP 815 V1.3 (2026-09-01) and its Annexes A to F and H.

Source: Contains public sector information licensed under the Open Government Licence v3.0. JSP 815 Defence Safety Management System V1.3 (Annex H V1.2), Ministry of Defence, © Crown copyright. Reconstructed reference notes; licence and source links in LICENSE.

How to Use This Skill

  • Without arguments: read the Core Frameworks below, the PDCA basis, the Element / Expectation / Performance Statement hierarchy, the 12 Elements, and the assurance stages.
  • With a topic: find it in the Topic Index and open the chapter it routes to.
  • With an Element or Expectation number (for example E4.7): use the Chapter Index to find which chapter carries that Element.
  • For a term: try glossary.md; for decision rules and checklists, try cheatsheet.md.

Chapters carry Sources: lines naming the attachment rows and the paragraph or Expectation numbers behind each claim. Performance Statements are summarised, never quoted; read the source Expectation tables for the exact wording.

Core Frameworks & Mental Models

The Defence SMS in one view

JSP 815 sets the Defence Safety Management System (SMS): a goal-based, non-prescriptive framework under which each Defence Area builds its own safety management arrangements within a common structure. Accountability is devolved; the Department sets Expectations, and Defence Areas conform to them through their own governance and operational context. The SMS is aligned to ISO 45001 but carries additional and different requirements to meet Defence needs, so ISO alignment is a claim the Framework makes, not an identity. The Defence Safety Function, led by the Director of Defence Safety & Support (Dir-DSS), owns the SMS, the Safety Operating Model, and second-line assurance against it.

Plan-Do-Check-Act basis

The SMS is organised on the four-stage Plan-Do-Check-Act cycle. Plan covers policy, governance, and planning; Do implements the arrangements and controls; Check measures performance and investigates failures; Act reviews and improves. The 12 Elements distribute across this cycle, and continual improvement is the loop that closes it.

Element / Expectation / Performance Statement hierarchy

The structure has three levels. Elements (12) divide Defence Area activity into safety topics. Each Element carries numbered Expectations (72 in total, E1.1 to E12.5) describing activities expected to be in place in a Defence Area's arrangements. Each Expectation is articulated by Performance Statements that show how compliance and continual improvement are demonstrated, with example performance across assurance levels from unsatisfactory to substantial. Cite Expectation numbers; treat Performance Statements as themes this pack summarises rather than text it reproduces.

The 12 Elements

  • E1 Leadership, Governance and Culture (6 Expectations): tone from the top, accountabilities, leadership visibility, resilient safety management.
  • E2 Organisation and Dependencies (8): safety management arrangements, roles, resources, consultation, changes, dependencies and interfaces. Annex A covers SEMS applicability.
  • E3 Legislation, Policy, Regulations and Guidance (5): compliance, Defence Area policy, communicating requirements, exemptions. Annex B covers the exemption certificate process.
  • E4 Risk Assessments and Safety Cases (7): hazard identification, risk management and elevation, communication, change tracking, safety cases.
  • E5 Supervision, Contracting and Control Activities (7): delegation of authority, risk elevation, letters of delegation, ceasing activities, safe systems of work. Annexes C and D cover duty of care on deployments and Head of Establishment responsibilities.
  • E6 Personnel Competence, Resources and Training (5): resources, delegation, people development, training, competency assessment. Annex E covers safety aspects of letters of delegation.
  • E7 Equipment Design, Manufacture and Maintenance (8): lifecycle risks, compliance, maintenance, supply chain, lessons, integration.
  • E8 Infrastructure Design, Build and Maintenance (7): the infrastructure counterpart to E7.
  • E9 Performance, Management Information and Reporting (4): monitoring, review, management information, leadership decisions.
  • E10 Accident / Incident Management and Emergency Response (5): reporting, recording, investigation, actions and learning, emergency and business continuity plans.
  • E11 Communications and Stakeholder Engagement (5): stakeholders, working relations, accessing safety information, raising concerns.
  • E12 Assurance (5): first, second, and third Lines of Defence assurance, annual self-assessment, leadership review, corrective action. Annex F maps Elements to ISO 45001 clause numbers; Annex H (V1.2) is the audit manual.

Assurance stages

Assurance levels are sequential and cumulative: unsatisfactory, limited, moderate, substantial. A Defence Area can only claim substantial assurance once moderate has been achieved. The assessment criteria are aligned with the Government Internal Audit Agency and ask three questions of key controls: are they embedded, do they help manage key risks, and do they operate as intended. Element 12 operationalises this through the three-Lines-of-Defence model: first-line assurance by those delivering the activity, second-line function assurance, and third-line independent audit per the Annex H manual.

Safety case trigger (E4.7)

A safety case is a structured argument, supported by evidence, that justifies a system as safe for a given application in a defined operating environment. The trigger: Defence work-related activity conducted on, or forming part of, a system where a single risk assessment of the activity or workplace is not sufficient to demonstrate adequate risk control, because of complexity, novelty, scale, or the risk profile. Simple, routine activity kept ALARP and tolerable by risk assessments and standard operating procedures does not need one. Scope is proportionate to risk and complexity, and equipment safety cases are treated in Element 7.

Exemption route (E3.5, Annex B)

Where compliance with safety legislation cannot be achieved, an exemption certificate from the Secretary of State for Defence is the route. The process is a last resort, used only after other avenues are exhausted. A sponsor builds an Exemption Case Summary, gets it endorsed, forwards it with a draft certificate for approval, and then provides a copy to the regulator, records the certificate, and manages its validity and renewal while control measures limit residual risk. Where no certificate is in place, the activity must conform.

Chapter Index

ChChapterSourcesPagesCoverage
01ch01-defence-safety-jsp-map.mdF (Foreword to Purpose; orientation only)~7 of 14Which JSP answers what: JSP 815 SMS, JSP 816 EMS, JSP 375, JSP 376, JSP 814, SofS Policy Statement, Safety Function Operating Model, DSA regulators. Duty of care scope. Orientation only.
02ch02-sms-structure-and-assurance-stages.mdF (Management system approach to Assurance stages)~7 of 14PDCA basis, Defence Safety Function role, Element / Expectation / Performance Statement hierarchy, ISO 45001 alignment claim, assurance stages.
03ch03-leadership-and-organisation.mdE1, E2, AA43Leadership, governance, culture; organisation and dependencies; SEMS applicability.
04ch04-legislation-and-exemptions.mdE3, AB24Legislation, policy, regulation and guidance; regulator relationships; exemption certificate process.
05ch05-risk-assessment-and-safety-cases.mdE423Risk profile, risk management and elevation, risk communication, change tracking, safety cases (Expectations 4.1 to 4.7).
06ch06-supervision-contracting-control.mdE5, AC, AD30Supervision, contracting, control of activity, duty holding reference, duty of care on deployments, Head of Establishment responsibilities.
07ch07-competence-and-delegation.mdE6, AE18Personnel competence, resources, training; safety aspects of letters of delegation.
08ch08-equipment-and-infrastructure.mdE7, E835Equipment design, manufacture, maintenance; infrastructure design, build, maintenance.
09ch09-performance-incidents-communication.mdE9, E10, E1139Performance and management information; accident and incident management, emergency response; communications and stakeholder engagement.
10ch10-assurance-and-audit.mdE12, AF, AH73Assurance, JSP 815 to ISO 45001 clause-number mapping (numbers only), audit manual method.

Topic Index

  • Assurance and audit → ch10
  • Communications and stakeholder engagement → ch09
  • Competence, training, letters of delegation → ch07
  • Contracting and control of activity → ch06
  • Duty of care on deployments → ch06
  • Equipment safety → ch08
  • Exemption certificates → ch04
  • Head of Establishment responsibilities → ch06
  • Incident and emergency management → ch09
  • Infrastructure safety → ch08
  • ISO 45001 mapping and alignment → ch10 (alignment claim in ch02)
  • Leadership, governance, safety culture → ch03
  • Legislation and regulators → ch04
  • Organisation and dependencies, SEMS applicability → ch03
  • Performance and management information → ch09
  • Risk assessment and safety cases → ch05
  • Safety management system structure and assurance stages → ch02
  • Supervision and duty holding → ch06
  • Which JSP applies → ch01

Supporting Files

  • glossary.md: Defence safety terms from the Framework and each Element's Terms and definitions, alphabetical, with chapter references.
  • cheatsheet.md: Element and Expectation index, assurance stages table, exemption certificate steps, safety case trigger checklist, audit cycle steps.

Scope & Limits

  • Source versions: JSP 815 Defence Safety Management System V1.3 (Framework, Elements 1 to 12, Annexes A to G) and Annex H Audit Manual V1.2, all published 2026-09-01; the pin was re-verified 2026-10-12. The notes were built from the 20 published PDF attachments in the sibling prototype; page provenance is in LICENSE.
  • Policy, not statute: JSP 815 is Ministry of Defence policy and guidance; it is not statute. Legal obligations come from legislation, and ch04 covers how the JSP relates to statute and regulators.
  • Not in this pack: No other JSP is reproduced. JSP 376 is now a separate pack: use jsp-376 for Defence acquisition safety policy. JSP 375, JSP 520, and JSP 816 are named by the source and by ch01 as related publications and are not in this catalogue; this pack names them by title and makes no claims about their contents. DEF-STAN standards are out of scope: DEF-STAN 00-051 is unverified as a public document and DEF-STAN 00-970 is not public; neither appears here. Annex G (Assurance Toolkit spreadsheet) is named in the pin but is not reproduced.
  • ISO 45001: clause numbers only, via the Annex F mapping. No ISO text is included.
  • Fidelity: Performance Statements are summarised as themes; Expectation wording is paraphrased except short defined terms. Chapters cite the attachment rows and paragraph or Expectation numbers behind each claim.
  • Status: this pack is not MOD guidance and has no official status; nothing in it suggests Ministry of Defence endorsement.
  • No external links: source and licence links live only in LICENSE.

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 Jsp 815 AI skill do?

Knowledge pack reconstructed from JSP 815 Defence Safety Management System V1.3 (Ministry of Defence, Open Government Licence v3.0): the SMS Framework, all 12 Elements with their Expectations and Performance Statement themes, and Annexes A to F plus H. Covers the Defence Safety Function and which JSP applies, leadership and safety culture, organisation and SEMS applicability, legislation and exemption certificates, risk assessment and safety cases, supervision and contracting, competence and letters of delegation, equipment and infrastructure safety, performance and incident management, and...

Why use Jsp 815 on TypingMind?

Because you install it once and use it with any model. Jsp 815 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 Jsp 815 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/jsp-815. 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 Jsp 815?

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 Jsp 815?

As many as you like. As long as a model supports skills, you can use Jsp 815 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Jsp 815 AI skill free?

It is published on GitHub by jgsystemsconsulting. Check the repository for licensing terms. 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 👇