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 yarlson/yarstack --skill cli-controlgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/cli-control)<a href="https://agentmods.dev/skills/yarlson/yarstack/cli-control"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/cli-control/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/yarlson/yarstack/cli-control"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/cli-control.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 | $0.00058 | $0.00534 |
| Opus 5.5 | $0.00023 | $0.00214 |
| Sonnet 5.5 | $0.00012 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
cli-control 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 3d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Control
Gather reproducible evidence from a terminal-hosted interface without changing production behavior.
Workflow
-
Identify the command, the working directory, the terminal conditions, and the observable contract.
-
Choose the method. Run ordinary output and exit-status checks directly or through the repository's tests. A command run through a pipe has no terminal, and many programs then skip prompts, colors, or line editing, so piped output does not prove terminal behavior. Use a pseudo-terminal for prompts, interactive input, signals, resizing, hangs, or restoration.
-
Bound every run with the host's command timeout or
timeout, so a hang becomes evidence instead of a stuck session. -
Prefer an existing trusted harness. Otherwise use
tmuxas the pseudo-terminal:tmux new-session -d -s probe -x 120 -y 40 tmux set-option -t probe remain-on-exit on tmux respawn-pane -k -t probe '<command>' tmux capture-pane -t probe -p # read the screen tmux send-keys -t probe 'text' Enter # type; C-c sends SIGINT tmux resize-window -t probe -x 80 -y 24 tmux display -p -t probe '#{pane_dead} #{pane_dead_status}' # exit status tmux kill-session -t probeWait for a state by polling
capture-panefor the expected text with a bounded number of attempts, not by fixed sleeps. -
Drive one action at a time, and capture the smallest transcript or measurement that proves or disproves the behavior.
-
Check interrupts, cleanup, exit status, hangs, and terminal restoration only where they matter to the contract.
-
Clean up only the sessions, processes, and files that this workflow created.
Keep verification read-only unless the parent task separately authorizes implementation. Use behavior-implement and test-design for fixes or regression tests. Do not send credentials or destructive commands, keep sensitive transcripts, or leave one-off harness code in the repository.
Result
Report the command and conditions, the observed output and exit status, the evidence, and any blocker or limitation.
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.
- 3d ago Changed · +14 lines · +16 tokens per session 8b22d5337446
- 1mo ago First seen · 24 lines · 42 tokens per session scan A e117f36d8754
cli-control is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 534 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
safe-change
Trace, implement, test, and independently review one bounded software change. Use for ordinary feature, bug-fix, or refactor work after the repository is bootstrapped; do not use for broad repository cleanup, production operations, or undefined rewrites.
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
Autonomous Agent Testing
Testing patterns for autonomous AI coding agents like Devin and SWE-Agent including task verification, output validation, sandboxed execution, regression testing for agent behavior, and safety guardrails for autonomous code generation.
ring:running-dev-cycle
Running the backend dev cycle: implements every task in a rolling-wave plan.md (ring:writing-plans format) for a Go/TS service, driving specialist agents through Gate 0 implementation/TDD, Gate 8 parallel review, and Gate 9 validation per epic, elaborating later phases at each phase boundary. Use when starting or…