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/jxoesneon/ciel/shellnpx skills add jxoesneon/Ciel --skill shellgit clone --depth 1 https://github.com/jxoesneon/CielWhat 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 | $0.00017 | $0.00401 |
| Opus 5 | $0.00009 | $0.00200 |
| Sonnet 5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
shell 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.
What it actually says
shell
Execute shell commands. All commands use the universal set defined in PLATFORM_AGNOSTIC_MAPPING.md.
Platform Agnosticism
- Internal reasoning always uses the Universal Command Set (
ls,cat,grep, etc.). - Internal paths always use POSIX-style forward slashes
/. - The active adapter's
shell()implementation performs OS-specific translation.
Operations
shell.run(cmd, cwd, env, timeout)— capture stdout/stderr/exit.shell.pipe([cmd, cmd])— piped sequences.shell.bg(cmd)— background (returns handle; managed by adapter).shell.which(bin)— PATH lookup.
I/O Contract
io_contract:
input: { cmd: string, "cwd?": path, "env?": map, "timeout_s?": int }
output: { stdout: string, stderr: string, exit: int }
idempotent: false
side_effects: [shell]
Safety
- Honours host permission rules (see
adapters/*/PERMISSIONS.md). - Refuses commands matching
configuration/local/rules.config.md.forbidden_ops. sudo+ privileged binaries are always mid+ risk.- Timeouts default to
acquisition.config.sandbox_limits.wall_sin sandbox contexts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 47 lines · 17 tokens per session scan A bfc5e6bb66c7
shell is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 401 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
user-defined-command
Create and edit Steward user-defined commands (UDCs). Use when the user wants to create, modify, or troubleshoot custom command workflows defined as YAML in the Steward/Commands folder.
stateful-widget
Build interactive HTML project widgets with persisted runtime state (games, counters, forms). Read before showwidget when user actions must survive reopening the note.
interactive-widget
Expose model-callable widget actions and configure turn-based play via Widget.md (actions, actors, agent blocks). Read after stateful-widget when humans and models take turns.
build-personal-brain
Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…
flashcard
Create and edit flashcards for spaced repetition learning. Use when the user wants to create, modify, format, or troubleshoot flashcards in their notes.
guardrails
Define safety rules to restrict AI from reading, listing, creating, editing, or deleting specific folders or files. Use when the user wants to set up guardrails, access rules, or protect sensitive areas.