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/dev-lou/pixelpilot/threat-modelinggit clone --depth 1 https://github.com/dev-lou/PixelPilotWhat 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 | $0.02760 | $0.02760 |
| Opus 5 | $0.01380 | $0.01380 |
| Sonnet 5 | $0.00552 | $0.00552 |
| Haiku 4.5 | $0.00276 | $0.00276 |
Grade A, and why
PixelPilot threat-modeling.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 yesterday.
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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Modelling 2026
STRIDE threat model → trust boundary diagram → threat table → mitigations → security test cases. Run before writing security-sensitive code.
THE STRIDE MODEL
| Letter | Threat | Violates | Example |
|---|---|---|---|
| S | Spoofing | Authentication | Attacker impersonates admin user |
| T | Tampering | Integrity | Attacker modifies request payload |
| R | Repudiation | Non-repudiation | User denies making a purchase |
| I | Information disclosure | Confidentiality | API leaks other users' data |
| D | Denial of service | Availability | Flood endpoint to make it unreachable |
| E | Elevation of privilege | Authorization | Regular user accesses admin endpoint |
STEP 1 — DECOMPOSE THE SYSTEM
Before applying STRIDE, map the system using Data Flow Diagrams (text format).
## System Decomposition
### Actors (external entities)
- **Anonymous user** — unauthenticated visitor
- **Authenticated user** — logged-in member
- **Admin** — internal staff with elevated access
- **Third-party service** — Stripe, OAuth provider, email service
### Processes
- **Auth service** — login, registration, session management
- **API gateway** — routes, rate limiting, auth middleware
- **Business logic** — core feature processing
- **Background workers** — async jobs (emails, reports)
### Data stores
- **Primary DB** — user records, transactions
- **Cache** — session tokens, temporary data
- **File storage** — user uploads (S3 / R2)
- **Audit log** — immutable event log
### Trust boundaries (draw these explicitly)
─────────────────────────────────────────
[ Internet / untrusted zone ]
↓ HTTPS ↓
[ Load balancer / WAF ] ← Trust boundary 1
↓
[ API gateway + rate limiter ] ← Trust boundary 2
↓
[ Application server ]
↓ ↓
[ Primary DB ] [ External APIs ] ← Trust boundary 3
─────────────────────────────────────────
STEP 2 — APPLY STRIDE TO EACH COMPONENT
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.
- yesterday First seen · 356 lines · 2,760 tokens per session scan A ec5cc08744bf
PixelPilot threat-modeling.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,760 tokens to every session, about $0.0138 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 2026-08-31.
Other instructions, from other repositories
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
healthcare-agents AGENTS.md
Instructions for ajhcs/healthcare-agents, covering healthcare agents repository instructions, repository map, git workflow and self-improvement loop.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
shenzjd-skills CLAUDE.md
Claude Code instructions for wu529778790/shenzjd-skills, covering claude.md, project overview, commands, a single skill's unit test and architecture.
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.
syncai copilot-instructions.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.