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/outlinedriven/outline-driven-development/control-clinpx skills add OutlineDriven/outline-driven-development --skill control-cligit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/control-cli)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/control-cli"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/control-cli.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 | $0.00042 | $0.00736 |
| Opus 5 | $0.00021 | $0.00368 |
| Sonnet 5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
control-cli 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 today.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- control-cli — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control CLI
Contract
| Field | Bound contract |
|---|---|
| Trigger | Reproduce, profile, or verify CLI/TUI behavior. |
| Authority | Reversible local: writes only temporary transcript or profile artifacts under a system temp directory and may spawn local PTY sessions; rollback is terminating the PTY process and removing its runtime scratch. No remote mutation. No source or VCS mutation. No credential or paid mutation. |
| Side effect | Runs temporary terminal sessions and captures evidence. |
| Done | A deterministic transcript or profile proof artifact exists and the live PTY session is terminated with its runtime scratch removed. |
Inputs
- The CLI/TUI binary or command to exercise (must be supplied).
- The exact reproduction steps, profile target, or verification scenario (must be supplied).
- Optional: expected output, timeout, and environment variables.
Procedure
- Create a fresh session directory under the system temp path for the captured artifact and PTY/tmux runtime scratch. Record the directory for cleanup. Done when: the session directory is created and recorded.
- Spawn the target CLI/TUI under a PTY, or a tmux session attached to a PTY, so interactive behavior is observable. Apply one action per observation: send one input, then capture the full terminal render before sending the next. Done when: the PTY or tmux session is spawned and interactive behavior is observable.
- For reproduction: drive the supplied steps in order, appending the terminal state after each action to the transcript artifact. Done when: every step is driven in order and the transcript artifact captures the terminal state after each action.
- For profiling: run the target under the chosen profiler, capturing timing or allocation output into the profile artifact. Done when: the profile artifact captures timing or allocation output.
- For verification: exercise the scenario, compare the observed output against the expected output when supplied, and record the pass or fail classification in the transcript artifact. Done when: the pass or fail classification is recorded in the transcript artifact.
- Terminate the PTY process, or detach and kill the tmux session. Done when: the PTY process or tmux session is terminated.
- Remove the PTY/tmux runtime scratch (pipes and sockets); the captured transcript or profile artifact file remains as the retained proof. Done when: runtime scratch is removed and the artifact file remains.
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.
- today Changed d869a3ad3d69
- 2d ago First seen · 41 lines · 42 tokens per session scan A 66f4d4cd158a
control-cli is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 736 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 2026-09-03.
Other skills, from other repositories
strict-validation-setup
Use when a user invokes a strict-mode validation or verifiable-goals loop setup. Bootstraps strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify. Don't use for remote, credential, publish, deploy, or irreversible changes.
validation-first-driven
Use when building protocols, workflows, concurrent systems, or lifecycle-heavy state that needs explicit states, transitions, and temporal properties. Defines the state machine, encodes invariants in types, and for high-risk designs runs a TLA+ or Alloy model checker. Not for encoding domain models in types — use…
testing-handbook-generator
Use when the user asks to discover, generate, refresh, or validate skills from the Trail of Bits Testing Handbook or appsec.guide. Not for tasks that require source or remote-system changes.
ios-device-qa
Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.
property-test-review
Use when reviewing existing property tests for coverage and defects. Reports tautological, vacuous, assertion-free, reimplemented, weak, or over-filtered tests with evidence, severity, and strongest replacement property. Not for generating tests — use property-test-authoring.
exhaustive
Use when asked to prove coverage, find missing cases, or enumerate a state, decision, requirement, or behavior space. Enumerates every cell as covered, gap, or deferred with an executed check per cell, and emits a coverage manifest with a tally. Not for round-based questioning — use askme; not for testing one property…