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.
npx agentmods add instructions/fortify/skills/copilot-instructionsgit clone --depth 1 https://github.com/fortify/skillsWhat 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 | $0.01613 | $0.01613 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
skills copilot-instructions.md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fortify Skills Repository
This is the public OpenText Fortify AppSec skills repository. It contains AI assistant skills following the Agent Skills standard, designed to teach AI coding assistants how to use Fortify effectively.
Structure
.
├── .claude-plugin/
│ ├── plugin.json # Claude Code plugin manifest (no version field — intentional)
│ └── marketplace.json # Claude Code marketplace catalog + version authority
├── .codex-plugin/
│ └── plugin.json # OpenAI Codex plugin manifest + version field
├── .agents/
│ └── plugins/
│ └── marketplace.json # OpenAI Codex repo-scoped marketplace catalog
├── gemini-extension.json # Gemini CLI extension manifest + version field
├── skills/ # The skills (Agent Skills spec)
├── agents/ # AI assistant agents (*.agent.md)
├── version.txt # Overall version (managed by release-please)
├── README.md # End-user documentation
├── CONTRIBUTING.md # Developer/contributor guide
└── LICENSE
Conventions
- Skill directories use kebab-case names
- SKILL.md frontmatter fields:
name,description, and optionaldisable-model-invocation,user-invocable,allowed-tools,context,argument-hint - Reference files are linked from SKILL.md and loaded on demand (progressive disclosure)
- Keep descriptions concise — they're loaded at startup for skill matching
- Skills must be assistant-agnostic: work with Claude Code, GitHub Copilot, Cursor, Gemini CLI, etc.
- Skills teach workflows using FCLI commands — the AI assistant executes them
- Leverage best practices where appropriate (https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
Workflow terminology
Use Step for all numbered workflow divisions — in SKILL.md, agent.md, and reference files. Do not use "Phase", "Stage", or "Phrase" as structural labels.
| Level | Term | Format | Where |
|---|---|---|---|
| Primary | Step | ## Step N: Name |
Top-level workflow divisions in SKILL.md and agent.md |
| Secondary | Step (lettered) | ### Step Na: Name |
Sub-actions within a Step |
| Gates | Step N gate | ### Step N gate or ### Step N → Step N gate |
Checklists between steps |
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.
- 2d ago First seen · 100 lines · 1,613 tokens per session scan A cc88cef84316
skills copilot-instructions.md is an instructions file published in the GitHub repository fortify/skills (19 stars, last pushed 1mo ago), licensed MIT. It adds 1,613 tokens to every session, about $0.0081 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 2026-08-30.
Other instructions, from other repositories
draugr CLAUDE.md
Instructions for draugr-dev/draugr, covering working on draugr, what draugr is, layout, before you open a pr and design principles.
copilot-security-instructions copilot-instructions.md
Instructions for Robotti-io/copilot-security-instructions, covering general markdown rules, yaml frontmatter conventions, authoring standards per file type, a) custom agent profiles: agents/.agent.md and b) prompt files: prompts/.prompt.md.
copilot-security-instructions mcp-server.development.instructions.md
Instructions for Robotti-io/copilot-security-instructions, covering mcp server development rules (this repo), core standards, express / http handling, mcp tools and logging hygiene.
copilot-security-instructions copilot-customization-files.instructions.md
Instructions for Robotti-io/copilot-security-instructions, covering instructions for copilot customization markdown files, required structure, frontmatter requirements by file type, .agent.md and .prompt.md.
copilot-security-instructions security-library-authoring.instructions.md
Instructions for Robotti-io/copilot-security-instructions, covering security library authoring rules (this repo), global requirements, root prompt files: prompts/.prompt.md, skills: skills//skill.md and agents: agents/.agent.md.
code-security-skill CLAUDE.md
Claude Code instructions for Chiehyii/code-security-skill, covering code security skill — claude.md, what this skill does, how to use the search engine, full security report for any feature and get checklist for file upload.