assets

A skill that defines how to delegate a focused, usually read-only investigation to R-Code, a local MCP service. MCP is a standard way for an assistant to use external tools.

In plain words
What is it for?
Use it when the user specifically asks R-Code to inspect an already opened workspace. Provide a concrete investigation goal and use full access only with explicit permission.
Why use it?
It sets boundaries so investigations use an approved workspace and do not accidentally edit files, run commands, or start further agents.

Skill for Claude CodeCodex

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 skills/foritin/r-code/assets
Any agent
npx skills add foritin/r-code --skill assets
Clone the repo
git clone --depth 1 https://github.com/foritin/r-code

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00339
Opus 5 $0.00000 $0.00169
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured yesterday against content hash d0b3f474601b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assets 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.

src-tauri/assets/SKILL.md · 30 lines

What it actually says

R-Code Collaboration

R-Code can be available as a local MCP server named r-code. Use it only when the user asks you to delegate a focused investigation to R-Code's own Agent.

Safe delegation flow

  1. Work only with a workspace_path that the user has already opened in R-Code. Do not guess paths or ask R-Code to inspect a different folder.
  2. Call r_code_delegate with a concrete goal. Omit access, or use access: "read_only", unless the user or parent task explicitly authorized edits for this delegated task.
  3. If the result is still running, call r_code_wait_for_result or r_code_task_status using the returned task_id.
  4. Use the returned concise result in your answer. A read-only result is not permission to write files, run commands, or delegate additional work.

Capability boundary

The R-Code MCP service creates a read-only task by default. Its Agent can inspect the already-approved workspace, but cannot edit files, run shell commands, create terminals, or spawn more agents. Use access: "full_access" only when an explicit authorization statement from the user or parent task is also supplied as authorization; R-Code still applies the project's approval policy. The MCP service never exposes provider credentials or Codex credentials.

Use r_code_cancel_task only to stop a task that this same MCP session started. Do not attempt to call undocumented terminal.*, ControlDoor, or environment variable interfaces; they are not part of the R-Code MCP contract.

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 · 30 lines · 0 tokens per session scan A d0b3f474601b

Subscribe to this mod's changes

assets is a skill published in the GitHub repository foritin/r-code (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 339 tokens. 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.