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/yehezkieldio/firefly/copilot-instructionsgit clone --depth 1 https://github.com/yehezkieldio/fireflyWhat 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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
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.
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:
Bunfor execution and package management. - Validation:
Zodfor 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
neverthrowfor explicit success/error handling. - No exceptions: EXPLICITLY DO NOT USE ANY
try/catchORthrowSTATEMENTS. - 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>.
- A synchronous
-
FireflyAsyncResult<T>- An asynchronous
ResultAsync<T, FireflyError>— behaves likePromise<Result<T, FireflyError>>. - Do not wrap it in
Promise. - Do not mark a function returning
FireflyAsyncResult<T>asasync.
- An asynchronous
-
Promise<FireflyResult<T>>- Use only when you need to
awaitinside the function body (e.g., to unwrap aFireflyAsyncResult). - This is the correct type for functions that internally
awaitother async operations and then return aFireflyResult.
- Use only when you need to
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 · 76 lines · 775 tokens per session scan A 1f69df1989d4
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.
Other instructions, from other repositories
fff AGENTS.md
AGENTS.md instructions for dmtrKovalenko/fff, covering to clankers, development commands, building, testing and development tools and code quality.
bunqueue CLAUDE.md
Instructions for egeominotti/bunqueue, covering bunqueue, test isolation rules, architecture flow, directory structure and code guidelines.
pi-coding-agent-forge AGENTS.md
Instructions for Firstp1ck/pi-coding-agent-forge, covering repository documentation rules, documentation goal, required documentation layers, readme.md — human guide and technical.md — advanced user reference.
rosetta pr-review-bots.instructions.md
How Copilot and CodeRabbit reviews manifest on a rosetta PR, why each looks different from a gh point of view, and what 'wrapping a PR' actually requires.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.