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/codealive-ai/ai-driven-development/installing-cli-toolsnpx skills add CodeAlive-AI/ai-driven-development --skill installing-cli-toolsgit clone --depth 1 https://github.com/CodeAlive-AI/ai-driven-developmentWhat 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 | $0.00094 | $0.01255 |
| Opus 5 | $0.00047 | $0.00628 |
| Sonnet 5 | $0.00019 | $0.00251 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
installing-cli-tools 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installing CLI Tools
Overview
Use this skill to take a CLI from "not installed" to "usable and verified" without exposing credentials in chat, logs, shell history, or repo files. Treat installation and secret setup as separate phases.
Workflow
- Identify the exact CLI, target OS/architecture, intended use, and whether authentication is required.
- Check current state with narrow commands such as
command -v tool,tool --version, package-manager queries, and existing config file paths only when needed. - Research current official installation docs before acting unless the user supplied an exact trusted source. Prefer official docs, package registry pages, signed release notes, or the upstream GitHub release.
- Choose the least surprising install method:
- Existing project manager (
brew,npm,pipx,uv tool,cargo install,go install) when official and maintained. - Vendor installer only when it is the official path and its behavior is understood.
- Manual binary install only after verifying architecture, checksum/signature when available, permissions, and destination.
- Existing project manager (
- Install to a user-writable, reversible location when possible. Avoid
sudounless the install path truly requires it and the user has agreed. - Wire PATH/completions only as narrowly as needed. Never edit shell startup files to add secrets.
- Configure authentication through a safe channel.
- Verify with
tool --version,tool doctoror equivalent, and a non-destructive authenticated command if relevant. - Report what changed, where files were placed, how to undo it, and whether any restart/new shell is needed.
Secret Handling
Never read, print, summarize, grep, or search for existing secret values in .env, shell rc files, keychains, SSH keys, cloud credential files, or password-manager vaults. Do not run broad commands like env, printenv, or recursive token searches.
For new credentials, use the safest supported option in this order:
- Browser/device OAuth or official
tool auth login. - The platform's secure setup flow or connector for that provider.
- OS credential store, such as macOS Keychain, through commands that accept the secret via stdin or hidden prompt.
- Tool-specific config command that prompts interactively and does not echo the input.
- A local secrets manager such as
op,bw,pass,gopass, ordirenvwith a secret backend, if the user already uses it. - A plaintext env file only when the user explicitly asks for it or the CLI has no safer option; write placeholders by default and set mode
0600.
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 · 87 lines · 94 tokens per session scan A ab3df77ab00d
installing-cli-tools is a skill published in the GitHub repository CodeAlive-AI/ai-driven-development (131 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,255 once invoked, about $0.0005 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
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-task
Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.
map-explain
Deep walkthrough of code, a diff, or the whole project — problem, entities, flow, load-bearing-line rationale, side effects, assumptions, breakage. Use when learning unfamiliar code or auditing a diff.
map-auto
Single-entry autonomous autopilot: routes a task through the existing MAP workflows via routetask, then drives the selected chain (map-plan -> map-efficient -> map-check -> map-review, as routed) end-to-end to a committed feature branch in one session, auto-approving routine workflow-control holds and hard-stopping on…
map-resume
Resume an interrupted MAP workflow from .map/ /stepstate.json checkpoint. Use when returning after context exhaustion, /clear, or a session crash mid-workflow. Do NOT use to start new work; use map-plan or map-efficient.