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 magnus919/agent-skills --skill cli-buildergit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/cli-builder)<a href="https://agentmods.dev/skills/magnus919/agent-skills/cli-builder"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/cli-builder/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/magnus919/agent-skills/cli-builder"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/cli-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01114 |
| Opus 5.5 | $0.00035 | $0.00446 |
| Sonnet 5.5 | $0.00018 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
cli-builder 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Builder
Treat a CLI as a contract between the tool and the agent. The contract includes
command names, --help, flags, output schemas, exit codes, stderr, and previews.
Keep this file as the workflow; load the linked references only when their
specialized guidance is needed.
When to Use
- Build a new CLI that an agent will discover and call.
- Refactor prompts, ambiguous commands, parser-hostile output, or false success codes.
- Add or review
--json,--dry-run,--yes, idempotency, or lazy authentication.
One Workflow
1. Discover the real contract
Define one CLI per service (except services sharing vendor authentication). Inspect real non-health read endpoints before coding, verify the actual authentication header and response shape, and capture the command tree and failure cases. Do not invent flags from API documentation alone. For HTTP clients, read the Python API client pattern.
Choose Bash for local wrappers and filesystem pipelines. Choose Python for HTTP, JSON, authentication state, or three-level command trees.
2. Build a predictable surface
Use one consistent verb/resource convention. Every command should be non-interactive
and flag-driven, reject unknown flags, and provide useful subcommand help with
concrete examples. Make normal output human-readable, but support --json with a
stable curated schema, normalized types, deterministic ordering, and no other stdout.
Send diagnostics to stderr with truthful non-zero exit codes.
For any state change, implement --dry-run before data-fetching or mutation, and
require an explicit --yes/--force gate for destructive work. Guard creation,
updates, and deletion so reruns are safe. Authentication must be lazy: --help and
safe dry-runs work without credentials.
Use the advanced patterns for chained dry-runs, third-party JSON, version-dependent behavior, and text matching. Use the Bash scaffold when a local shell wrapper is the right fit.
What ships with it
9 files 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.
- evals/evals.json 7.5 KB
- README.md 1.7 KB
- references/advanced-patterns.md 6.8 KB
- references/agent-readiness-checklist.md 765 B
- references/improvement-cycle.md 2.5 KB
- references/mcp-vs-cli.md 3.5 KB
- references/python-api-client.md 10 KB
- references/skill-wrapper-example.md 3.8 KB
- templates/bash-cli-scaffold.sh 6.0 KB runs code
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 · -396 lines · +20 tokens per session 04b8f8f832c0
- 1mo ago First seen · 500 lines · 68 tokens per session scan A b2f426a0a09d
cli-builder is a skill published in the GitHub repository magnus919/agent-skills (147 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,114 once invoked, about $0.0004 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
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.
discuss
Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.