forge-cli

A set of design and testing instructions for command-line programs—tools operated through a terminal by typing commands and options. It treats command arguments, output, and exit codes as the program's interface for both people and other software.

In plain words
What is it for?
Use it when building or reviewing terminal commands, argument parsing, subcommands, pipelines, dry runs, error handling, and cross-platform behavior.
Why use it?
A command-line tool can appear to work interactively while failing in scripts or automated builds. These instructions focus on predictable help text, errors, input, output, and status codes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/forgeyclap/claude-forge/forge-cli
Any agent
npx skills add ForgeyClap/claude-forge --skill forge-cli
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.01355
Opus 5 $0.00023 $0.00678
Sonnet 5 $0.00009 $0.00271
Haiku 4.5 $0.00005 $0.00136

Measured yesterday against content hash 75bf2be89200, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-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 yesterday.

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.

.claude/skills/forge-cli/SKILL.md · 41 lines

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.

Forge playbook — Command-line tool / CLI

Do not duplicate ECC skills — defer to: the language reviewer skills (python-reviewer, typescript-reviewer, go-review, rust-review, etc. by stack) for idiomatic code, and /test-coverage for the test gate. This file is orchestration only.

A CLI is a contract with other programs, not just humans. It is invoked by scripts, pipelines, CI, and other tools — so its arg surface, exit codes, and stdio behavior are the real API. build-boss implements; test-boss drives the exit-code + pipe integration tests; docs-boss produces the --help/usage/README. Never claim "cross-platform" for an OS you did not actually run on (see honest limit).

Hard rules (non-negotiable)

  • Real arg parser + --help + --version. Use the stack's established parser (argparse/click, commander/yargs, clap, cobra) — not hand-rolled argv slicing. --help and --version always work and exit 0; usage is clear and shows at least one example; unknown flags fail with a helpful message, not a stack trace.
  • Correct exit codes. 0 = success only; distinct non-zero codes for distinct failure classes (usage error, not-found, permission, runtime). Never exit 0 on failure — pipelines and CI branch on the exit code. Document the code table.
  • Pipe / stdio discipline. Machine output → stdout; diagnostics, logs, prompts, progress → stderr (so cmd | other stays clean). Read stdin when piped / when the input arg is -. Offer a --json (or --quiet) mode for scripting. Respect non-TTY and NO_COLOR: no colors, spinners, or interactive prompts when output is piped or stdin is not a terminal. Don't crash on SIGPIPE/broken pipe (head closing early is normal).
  • No destructive default. Any irreversible action (delete, overwrite, force-push, truncate, mass-rename) is NEVER the default: require an explicit flag or an interactive confirmation, offer --dry-run to preview, and gate override behind --force/--yes. A bare invocation must be safe.
  • Testable — I/O separated from logic. Core behavior lives in pure functions callable without spawning a process; the thin CLI layer wires args → core → streams. Ship real tests that assert exit codes, stdout, stderr, and pipe round-trips (not just one happy path).
  • Cross-platform. Use the platform path API (no hardcoded / or \), tolerate CRLF/LF, don't assume a POSIX-only shell or GNU-only flags, and handle Ctrl-C (SIGINT) cleanly. Secrets/tokens come from env or a config file — never echoed to stdout/stderr or baked into the binary.

Read the full file on GitHub · 41 lines

Changes

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.

  1. yesterday First seen · 41 lines · 47 tokens per session scan A 75bf2be89200

Subscribe to this mod's changes

forge-cli is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 1,355 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 2026-08-31.

Related

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.

bytedance/deer-flow · 24 tokens

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…

software-mansion/argent · 107 tokens

review-offered-task

Review a task that has been offered to you and decide whether to accept or reject it.

desplega-ai/agent-swarm · 22 tokens

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…

tinyfish-io/tinyfish-cookbook · 169 tokens

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.

ai-driven-dev/framework · 66 tokens

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…

termio-sh/termio · 68 tokens