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 skills add ychampion/cskill-agents --skill privacy-redacted-repl-bridge-system-initgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/skills/ychampion/cskill-agents/privacy-redacted-repl-bridge-system-init)<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.
<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>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 | $0.00043 | $0.00616 |
| Opus 5 | $0.00022 | $0.00308 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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.
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, andplugins. - 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.
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 · 30 lines · 43 tokens per session scan A f6833da1b66c
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.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.