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/jtgsystems/custom-modes-roo-code/agents-mdgit clone --depth 1 https://github.com/jtgsystems/Custom-Modes-Roo-CodeWhat 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 | $0.01223 | $0.01223 |
| Opus 5 | $0.00611 | $0.00611 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
Custom-Modes-Roo-Code AGENTS.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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Senior Maintainer Contract
- Purpose: keep this repository stable, secure, well-tested, and aligned with existing patterns.
- Default mode: smallest safe change that solves the verified problem.
- Do not guess conventions.
- Do not disable tests, lint, type checks, or security controls to make a change pass.
- Do not introduce major-version dependency upgrades without a migration plan and a dedicated PR.
Repository Snapshot
- Repository:
jtgsystems/Custom-Modes-Roo-Code - Default branch:
main - Visibility:
public - Summary: Custom modes for Roo Code VS Code extension - Enhanced AI coding assistance configurations
- Detected stack: mixed or uncategorized source repo
Read First
README.mdCONTRIBUTING.mdCLAUDE.md.github/workflows/
Key Paths
scripts/assets/agents/custom_modes.d/schemas/vs-code/
Directory Guidance
scripts/: keep maintenance scripts idempotent and document environment assumptions.
Repository Rules
- Keep changes focused on the task and match the existing file layout and naming patterns.
- Update tests and docs when behavior changes or public interfaces move.
- Do not commit secrets, credentials, ad-hoc exports, or large generated artifacts unless the repository already tracks them intentionally.
- Prefer the existing automation and CI workflow over one-off commands when both paths exist.
Global Best Practices
- Understand the repo before editing: read the local guidance, README, docs, and relevant tests first.
- Follow existing architecture, conventions, and tooling; do not guess stack-specific patterns when the repo already defines them.
- Make the smallest safe change that solves the real problem, and prefer focused diffs over broad rewrites.
- Verify changes with the repo's actual checks, and add or update regression tests for behavior changes when practical.
- Keep public APIs and backward compatibility stable unless the task explicitly allows a breaking change.
- Do not overwrite user work, unrelated changes, or existing security controls just to make a check pass.
- Update docs when commands, config, setup, architecture, or user-visible behavior changes.
- If the change is ambiguous or high-risk, stop and produce a safe partial fix or a clear plan instead of guessing.
- Leave clear notes on what changed, why it changed, what checks ran, and any remaining risk.
- Legacy agent guidance exists in
CLAUDE.md; keep it aligned withAGENTS.mdif those files remain in use. - Avoid archive-style folders unless the task explicitly targets them:
.retired/.
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.
- 2d ago First seen · 104 lines · 1,223 tokens per session scan A 17ca290cef75
Custom-Modes-Roo-Code AGENTS.md is an instructions file published in the GitHub repository jtgsystems/Custom-Modes-Roo-Code (182 stars, last pushed 3mo ago), licensed MIT. It adds 1,223 tokens to every session, about $0.0061 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
dotnet-pilot CLAUDE.md
Instructions for zdanovichnick/dotnet-pilot, covering claude.md, repository context, layout, authoring rules and validating plugin changes.
rule-link AGENTS.md
AGENTS.md instructions for hangboss1761/rule-link, covering agents.md, project overview, development commands, architecture and core modules.
rule-link CLAUDE.md
Claude Code instructions for hangboss1761/rule-link, a project described as: A CLI tool to manage AI programming tool rule files through symlinks.
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).