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/lukacf/meerkat/shell-patternsnpx skills add lukacf/meerkat --skill shell-patternsgit clone --depth 1 https://github.com/lukacf/meerkatWhat 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 | $0.00012 | $0.00347 |
| Opus 5 | $0.00006 | $0.00173 |
| Sonnet 5 | $0.00002 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00035 |
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 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 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.
Operating Rules
- Use
shellfor short foreground commands. - For ordinary long-running commands, use
shellwithbackground: true, keep the returnedjob_id, then inspect withshell_job_statusor list jobs withshell_jobs. - 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.
- 2d ago First seen · 35 lines · 12 tokens per session scan A fe94b5694db3
Shell Patterns is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 347 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 2026-08-30.
Other skills, from other repositories
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…