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 lukacf/meerkat --skill shell-patternsgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/shell-patterns)<a href="https://agentmods.dev/skills/lukacf/meerkat/shell-patterns"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/shell-patterns/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/lukacf/meerkat/shell-patterns"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/shell-patterns.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 | $0.00012 | $0.00461 |
| Opus 5.5 | $0.00005 | $0.00184 |
| Sonnet 5.5 | $0.00002 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
Shell Patterns 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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell Patterns
Use shell tools for concrete local commands, verification, and long-running processes. Keep commands scoped to the user's workspace and report important results back into the conversation.
Background Prerequisites
background: true requires canonical session and operation bindings plus a
persistent realm job store, persistent blob store, and delivery projector.
Shell availability alone does not provide these resources: a shell-enabled
standalone or ephemeral composition can reject background execution with a
typed tool error. There is no process-local detached-job fallback. Use
foreground shell there (background: false, the default).
Operating Rules
- Use
shellfor short foreground commands. - When the durable runtime above is wired, use
shellwithbackground: truefor ordinary long-running commands. Keep the returnedjob_id, then inspect withshell_job_statusor list jobs withshell_jobs. A queued receipt acknowledges submission, not command success; inspect the terminal result before claiming completion. - A background shell submission is durable, but its worker is explicitly
non-resumable. After a restart the job record remains and a lost worker
becomes
worker_lost; Meerkat does not silently replay the command. - Use
monitor_startonly when that high-trust tool is explicitly visible and the script follows its declared protocol. Framed JSONL can emit typed notification, checkpoint, progress, and complete frames; notifications do not complete the job. - Cancel stuck or obsolete jobs with
shell_job_cancel. - Shell output is truncated. Shape large output with tools such as
rg,head,tail, or structured command flags. - Set the working directory intentionally. Prefer absolute paths when a command crosses project boundaries.
- Treat shell output as evidence to reason from, not as durable work state. Add WorkGraph evidence separately when a shared item needs proof.
- Shell is classified as mutating because Meerkat cannot prove an arbitrary command is read-only. It is unavailable under read-only tool policy.
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.
- 1mo ago Changed · +11 lines 6e4e0f3dd8bc
- 1mo ago First seen · 35 lines · 12 tokens per session scan A fe94b5694db3
Shell Patterns is a skill published in the GitHub repository lukacf/meerkat (23 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 461 once invoked, about $0.0000 per session on Opus 5.5. 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
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern. For many independent single-turn transforms (translate/rewrite/extract each file into a new file) that can wait…
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
loop
Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.
termio
See and drive the sibling agent sessions running alongside you in this Termio project via the termio session CLI — list and watch their status, spawn new agent or plain-terminal sessions, send a prompt or an answer into a session, and read an agent's reply from its transcript. Use when delegating work to another…
outcome-brief
Close substantive implementation, investigation, review, or research work with a short, consistently ordered, evidence-backed handoff. Use when a task reaches a terminal outcome; when the user asks what shipped, what changed, what needs attention, or what happens next; or when a host hook requests a valid Brief-Spec…
audiobook-maker
A workflow for turning long text, novels, and reports into spoken audio files. Text longer than 3,000 Chinese characters is split into smaller sections before speech is generated.