privacy-redacted-repl-bridge-system-init

privacy-redacted-repl-bridge-system-init is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 43 tokens per session (616 once invoked), scanned A, original, MIT.

A session-initialisation pattern that sends complete capability details to trusted clients and redacted details to remote clients. Redaction removes local tool, integration, and file-path information that could expose the developer's environment.

In plain words
What is it for?
Use it when a coding agent shares its available tools, MCP connections, plugins, commands, agents, or skills during startup.
Why use it?
It lets different connection types use the same message format while reducing the amount of private local information sent through remote or persistent channels.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a coding agent shares its available tools, MCP connections, plugins, commands, agents, or skills during startup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init
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.

Any agent
npx skills add ychampion/cskill-agents --skill privacy-redacted-repl-bridge-system-init
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for privacy-redacted-repl-bridge-system-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init)
Your own site
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for privacy-redacted-repl-bridge-system-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.00616
Opus 5 $0.00022 $0.00308
Sonnet 5 $0.00009 $0.00123
Haiku 4.5 $0.00004 $0.00062

Measured 6d ago against content hash f6833da1b66c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

privacy-redacted-repl-bridge-system-init 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.

agents/claude-code/skills/privacy-redacted-repl-bridge-system-init/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Privacy-Redacted REPL Bridge System Init

Domain: transport-privacy Trigger: Use when the same session-init or capability payload is emitted to both trusted SDK/internal consumers and remote transports that may persist or forward the metadata. Source Pattern: Distilled from reviewed remote-control, bridge transport, and capability-advertising implementations.

Core Method

Centralize init-payload construction in one shared builder so every transport keeps the same wire shape. At the call site, classify the transport by trust and persistence. For trusted SDK or internal paths, pass the full tool, MCP, and plugin inventories because those consumers depend on complete metadata. For remote bridge or other persisted transports, reuse the same builder and field names but pass redacted substitutes for leak-prone collections, especially tool names that expose MCP integrations, MCP server descriptors, and plugin paths that reveal usernames or project layout. Preserve only the metadata the remote client actually needs, such as model, permission mode, remote-safe commands, agents, skills, and fast-mode state.

Key Rules

  • Reuse one payload builder for all paths; vary the inputs, not the schema, so clients and tests get shape parity.
  • Treat any field that discloses local integrations or filesystem structure as sensitive on persisted or forwarded transports; in this seam that means tools, mcp_servers, and plugins.
  • Redact by omission or empty collections rather than partially fabricating local details; the remote client should see "not advertised," not misleading host metadata.
  • Keep trust-scoped fields that the remote UX genuinely needs, and further filter them to the remote-safe subset; for example, expose only bridge-safe slash commands rather than the full local command catalog.
  • Allow fuller metadata on trusted SDK/internal paths where telemetry and UI consumers explicitly rely on it; the privacy rule is transport-specific, not a blanket removal everywhere.

Read the full file on GitHub · 30 lines

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. 6d ago First seen · 30 lines · 43 tokens per session scan A f6833da1b66c

Subscribe to this mod's changes

privacy-redacted-repl-bridge-system-init is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 616 once invoked, about $0.0002 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 2026-09-03.