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/rjroy/vibe-garden/copilot-instructionsgit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/rjroy/vibe-garden/copilot-instructions)<a href="https://agentmods.dev/instructions/rjroy/vibe-garden/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/rjroy/vibe-garden/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 5.1 | $0.00476 | $0.00476 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
vibe-garden 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Code Review Instructions
Confidence Threshold
Only comment when confidence exceeds 80%. If you are uncertain whether something is an issue, do not comment.
Response Format
- Problem statement (one sentence)
- Why it matters (one sentence)
- Suggested fix with code snippet (if applicable)
Be concise. One sentence per comment when possible.
Do NOT Comment On
Language Semantics You Frequently Misread
- Python conditional expressions (
x if condition else yevaluates condition first) - Python's
zip(strict=True)already validates length; don't suggest redundant checks - Truthiness checks in conditional expressions happen before the truthy branch executes
Redundant Suggestions
- Adding validation before built-in safety mechanisms
- Explicit checks that duplicate what a parameter/flag already does
- Error handling for conditions that cannot occur by construction
Style and Formatting
- These are handled by ruff (Python)
- Do not comment on import ordering, line length, or formatting
Preference Items
- Parameter tuning suggestions that are subjective, not defects
- "Consider using X instead of Y" when both are valid approaches
- Refactoring suggestions not related to correctness
Documentation
- Missing docstrings or type hints (unless obviously wrong)
- Comments that restate what code already expresses
DO Comment On
Security (High Priority)
- Injection risks (SQL, command, template)
- Credential exposure or hardcoded secrets
- Missing input validation at system boundaries
- Unsafe deserialization
Correctness (High Priority)
- Logic errors with clear evidence
- Race conditions
- Resource leaks (unclosed files, connections)
- Off-by-one errors
- Null/None dereference risks
Error Handling
- Missing error handling at external boundaries (API calls, file I/O)
- Swallowed exceptions that hide failures
- Error messages that leak sensitive information
Architecture
- Code that violates patterns established elsewhere in the codebase
- Breaking changes to public APIs without deprecation
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.
- 6d ago First seen · 79 lines · 476 tokens per session scan A 6255421d1856
vibe-garden copilot-instructions.md is an instructions file published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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 2026-08-31.
Other instructions, from other repositories
sideboard CLAUDE.md
Instructions for mmyslin/sideboard: Sideboard's own roadmap lives in GitHub Issues (mmyslin/sideboard). The project is GitHub-only — there is no roadmap.json / local-file mode.
project-architect CLAUDE.md
Claude Code instructions for arnwaldn/project-architect, covering project-architect — plugin claude code, architecture, fichiers clés, conventions and workflow de développement.
recursive-spine CLAUDE.md
Claude Code instructions for slopstopper/recursive-spine, covering recursive-spine — rules codex, mission, house rules, tracking (recursive-spine convention) and ci gates.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).