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 skills/ychampion/cskill-agents/cross-shell-command-safety-mapsnpx skills add ychampion/cskill-agents --skill cross-shell-command-safety-mapsgit 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/cross-shell-command-safety-maps)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/cross-shell-command-safety-maps"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/cross-shell-command-safety-maps.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 | $0.00035 | $0.00412 |
| Opus 5 | $0.00017 | $0.00206 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
cross-shell-command-safety-maps 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 5d 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.
What it actually says
SKILL: Cross Shell Command Safety Maps
Domain: security Trigger: Apply this when you need to enforce identical permissions across bash/PowerShell, detect UNC paths, and keep dangerous config files hidden to both shells. Source Pattern: Distilled from reviewed permission, shell-safety, and worktree-management implementations.
Core Method
Maintain one shared policy source for command allowlists, UNC-path rejection, and sensitive-path checks, then have both the Bash and PowerShell entrypoints consume that same policy. Each shell may parse its own command syntax, but the decisions about what is read-only, what path patterns are dangerous, and when to reject remote shares should come from the same central maps. This keeps cross-platform behavior aligned and prevents one shell surface from quietly drifting into a weaker security posture.
Key Rules
- Only include commands that behave predictably across both shells; the shared allowlist should stay conservative and portable.
- Perform UNC detection before executing commands on Windows, covering backslash, forward slash, mixed separators, IPv4/IPv6 addresses, and WebDAV patterns.
- Normalize candidate paths before comparison and reuse the same sensitive-path deny rules in both shell tools.
- Keep these maps static so callers can memoize them and still share them among multiple shell entry points.
Example Application
When launching either shell tool, load the shared read-only command map and run the same UNC-path and sensitive-path checks before execution. A path that is rejected in Bash should be rejected for the same reason in PowerShell.
Anti-Patterns (What NOT to do)
- Don’t re-derive UNC heuristics per tool; this invites Windows credential-exfiltration bugs.
- Don’t treat UNIX-only commands as cross-shell safe; the shared list must be conservative and portable.
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.
- 5d ago First seen · 28 lines · 35 tokens per session scan A 781f73d3bd07
cross-shell-command-safety-maps is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 412 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 2026-08-30.
Other skills, from other repositories
rpce-merge-pr-batch
Safely process an explicitly ordered batch of RepoPrompt CE pull requests end to end: preserve a dirty original checkout, isolate each PR in an external disposable worktree, use window- and context-scoped CE rpce-cli Agent Mode review, repair and validate, require exact-head hosted checks, merge with merge commits…
rpce-test-quality
Select, design, review, consolidate, or remove RepoPrompt CE tests, diagnostic harnesses, and smoke checks by regression value and maintenance cost. Use when the task centers on test, diagnostic, or smoke coverage, including whether a single regression test is worth committing. Do not use for feature or bug-fix work…
rpce-contribution-check
Validate RepoPrompt CE contributions before committing or pushing. Use whenever an agent is about to create a commit, push the current branch, rewrite history, delete a branch or fork, or change GitHub-visible repository state. Enforces staged-index and outgoing-range secret scanning, repository guardrails, clean push…
rpce-release
Build or publish RepoPrompt CE release artifacts using the repository release scripts and GitHub workflows.
rpce-maintainer-guidance
Apply evidence-led RepoPrompt CE maintainership principles distilled from documented project guidance. Use when planning, scoping, implementing, reviewing, triaging, or sequencing RPCE changes; deciding whether work should be an investigation, issue, PR, or follow-up; checking compatibility, migrations, performance…
rpce-swift-6-concurrency-migration
Plan, inventory, stage, execute, or review RepoPrompt CE's project-wide migration to Swift 6.2 concurrency checking and Swift 6 language mode. Use when auditing packages, targets, settings, diagnostics, unsafe escape hatches, migration phases, blockers, or validation evidence across the root and provider packages. Do…