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/faramesh/faramesh-core/copilot-instructionsgit clone --depth 1 https://github.com/faramesh/faramesh-coreWrote 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/faramesh/faramesh-core/copilot-instructions)<a href="https://agentmods.dev/instructions/faramesh/faramesh-core/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/faramesh/faramesh-core/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 | $0.00210 | $0.00210 |
| Opus 5 | $0.00105 | $0.00105 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
faramesh-core 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 3d ago.
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.
What it actually says
Faramesh Core Copilot Instructions
Execution Order (Hard Requirement)
Never default to the fastest, easiest, or lowest-effort task order.
Always execute work in structural usability order for real users and agent runtimes:
- Interception path correctness
- Patching/autoload correctness
- Action governance runtime behavior
- HITL/defer runtime behavior
- Policy/FPL compilation and load path correctness
- Identity fail-closed behavior
- Credential sequestration fail-closed behavior
- Onboarding/reporting UX
- Tests, CI wiring, and E2E acceptance gates (last)
Prioritization Rule
If a lower-layer runtime capability is incomplete, do not move to convenience, reporting, or process layers.
Do not prioritize work because it is quicker to implement. Prioritize work that makes Faramesh operational and safe in production runtime flows.
Validation Timing
Testing and CI are required, but only after the runtime-critical path above is built and wired end-to-end.
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.
- 3d ago First seen · 27 lines · 210 tokens per session scan A d577f88972df
faramesh-core copilot-instructions.md is an instructions file published in the GitHub repository faramesh/faramesh-core (102 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 210 tokens to every session, about $0.0011 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 2026-08-30.
Other instructions, from other repositories
copilot-agents-dojo copilot-instructions.md
Instructions for andreaswasita/copilot-agents-dojo, covering copilot instructions, code standards, typescript (default example), python and java.
copilot-agents-dojo AGENTS.md
Instructions for andreaswasita/copilot-agents-dojo, covering copilot agents dojo — contributor guide, project structure, adding a skill, adding a cli command and testing.
ACGM-for-Claude-Code CLAUDE.md
Claude Code instructions for johnrucnapier-sketch/ACGM-for-Claude-Code, covering claude.md — project working agreement, precedence, evidence before ritual, high-risk operations and truth sources.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.