skillfoundry copilot-instructions.md

skillfoundry copilot-instructions.md is an instructions file for GitHub Copilot from samibs/skillfoundry. It costs 1,341 tokens per session, scanned A, original, MIT.

Copilot instructions for samibs/skillfoundry, covering github copilot — skillfoundry project instructions, identity, non-negotiable rules, code quality and security.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/samibs/skillfoundry/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for skillfoundry copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/samibs/skillfoundry/copilot-instructions.svg)](https://agentmods.dev/instructions/samibs/skillfoundry/copilot-instructions)
Your own site
<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>
Per session 1,341 This file is loaded in full into every session.
When invoked 1,341 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured today against content hash 456d08e3a5c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.github/copilot-instructions.md · 120 lines

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 later comments
  • 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 be undefined — 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 localStorage or sessionStorage
  • NEVER hardcode API keys, secrets, or credentials
  • NEVER expose stack traces in production responses
  • ALWAYS use HttpOnly + Secure + SameSite=Strict cookies 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.

Read the full file on GitHub · 120 lines

Changes

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.

  1. today First seen · 120 lines · 1,341 tokens per session scan A 456d08e3a5c9

Subscribe to this mod's changes

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.