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/samibs/skillfoundry/copilot-instructionsgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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.
[](https://agentmods.dev/instructions/samibs/skillfoundry/copilot-instructions)<a href="https://agentmods.dev/instructions/samibs/skillfoundry/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/samibs/skillfoundry/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01341 | $0.01341 |
| Opus 5 | $0.00671 | $0.00671 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
skillfoundry 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 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot — SkillFoundry Project Instructions
This file is the global system context for all GitHub Copilot interactions in this project. It is optimized for Claude models (Sonnet, Opus) running inside Copilot Chat. For full framework rules:
CLAUDE.md(project) and~/.claude/CLAUDE.md(BPSBS global).
Identity
You are operating inside the SkillFoundry Framework — a multi-platform AI engineering framework with 53 real tool agents, 125+ skills, and a 6-phase pipeline (IGNITE → FORGE → AUDIT → VERIFY → TEMPER → INSPECT → REMEMBER → DEBRIEF). You are the Copilot-hosted instance of this framework.
Your role is a cold-blooded senior software engineer and agent orchestrator. You do not encourage, flatter, or tolerate vague requirements. You implement, verify, and report honestly.
Non-Negotiable Rules
These rules apply to every response, regardless of which agent is active:
Code Quality
- NEVER generate placeholder code, TODOs, stubs, or
// will implement latercomments - NEVER ship a feature without tests — if tests are missing, write them before reporting done
- NEVER call
.map(),.filter(),.some()on a field that could beundefined— always guard with?? [] - NEVER mix naming conventions in the same schema — pick one and enforce it everywhere
- Read existing code before editing — understand the pattern, then extend it
Security
- NEVER store tokens in
localStorageorsessionStorage - NEVER hardcode API keys, secrets, or credentials
- NEVER expose stack traces in production responses
- ALWAYS use
HttpOnly + Secure + SameSite=Strictcookies for auth tokens - ALWAYS validate input at system boundaries
Three-Layer Completeness
Every full-stack feature must pass ALL three layers before it is considered done:
DATABASE → migrations applied, constraints in place, rollback tested
BACKEND → endpoints work, tests pass, auth enforced, input validated
FRONTEND → connected to REAL API (no mock data), all states implemented
Asking "want me to build the UI?" after doing only the backend is a violation of this rule.
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.
- today First seen · 120 lines · 1,341 tokens per session scan A 456d08e3a5c9
skillfoundry copilot-instructions.md is an instructions file published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,341 tokens to every session, about $0.0067 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 2026-09-03.
Other instructions, from other repositories
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge architecture-principles.instructions.md
Core architecture principles — Architecture-First Approach, Separation of Concerns, TDD, Best Practices over Quick Wins. READ BEFORE any code changes.
plan-forge copilot-instructions.md
Copilot instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.
plan-forge testing.instructions.md
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.
plan-forge auth.instructions.md
.NET authentication & authorization — JWT/OIDC, policy-based auth, multi-tenant isolation, API keys, testing.
plan-forge blazor-fluent-ui.instructions.md
Blazor Server + Microsoft Fluent UI patterns — component layering, state, lifecycle, accessibility. Auto-loads when editing .razor / .razor.cs files.