firefly copilot-instructions.md

Copilot instructions for yehezkieldio/firefly, covering development instructions, firefly, 1. technology stack, 2. coding standards and 3. coding patterns.

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/yehezkieldio/firefly/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/yehezkieldio/firefly

Made for: GitHub Copilot.

Per session 775 This file is loaded in full into every session.
When invoked 775 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00775 $0.00775
Opus 5 $0.00387 $0.00387
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured yesterday against content hash 1f69df1989d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

firefly 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 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.

.github/copilot-instructions.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Instructions

Firefly

Firefly is a CLI orchestrator for automatic semantic versioning, git-cliff changelog generation, and creating release all in one command.

1. Technology Stack

  • Runtime: Bun for execution and package management.
  • Validation: Zod for runtime validation and compile-time type inference.

2. Coding Standards

  • YAGNI Principle: Start simple and add complexity only when you have concrete requirements for it.
  • Defensive Programming: Validate all inputs/outputs at boundaries; treat external data as potentially invalid.
  • Readable & Intentional: Code should convey why it exists; avoid redundant comments on how it works.
  • Extract Complex Expressions: Break down complex expressions into well-named intermediate variables or functions/classes.

3. Coding Patterns

  • Locality of Behavior: Keep related logic close together.
  • Inward Dependency Flow: Outer layers depend on inner layers, never the reverse.
  • Explicit Interfaces: Define clear contracts between layers and modules.
  • Performance: Optimize by default and avoid common pitfalls; favor clarity over premature micro-optimizations.

4. Result & Error Handling

  • Rust-Style Semantics: Use neverthrow for explicit success/error handling.
  • No exceptions: EXPLICITLY DO NOT USE ANY try/catch OR throw STATEMENTS.
  • Explicit Unpacking: Use isOk() / isErr() guards for clarity and control flow.
  • Shallow Method Chains: Limit chaining to two links; use named variables for intermediate results.

Types

  • FireflyResult<T>

    • A synchronous Result<T, FireflyError>.
  • FireflyAsyncResult<T>

    • An asynchronous ResultAsync<T, FireflyError> — behaves like Promise<Result<T, FireflyError>>.
    • Do not wrap it in Promise.
    • Do not mark a function returning FireflyAsyncResult<T> as async.
  • Promise<FireflyResult<T>>

    • Use only when you need to await inside the function body (e.g., to unwrap a FireflyAsyncResult).
    • This is the correct type for functions that internally await other async operations and then return a FireflyResult.

Read the full file on GitHub · 76 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. yesterday First seen · 76 lines · 775 tokens per session scan A 1f69df1989d4

Subscribe to this mod's changes

firefly copilot-instructions.md is an instructions file published in the GitHub repository yehezkieldio/firefly (10 stars, last pushed 2mo ago), licensed MIT. It adds 775 tokens to every session, about $0.0039 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 2026-09-02.