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/forgeyclap/claude-forge/forge-clinpx skills add ForgeyClap/claude-forge --skill forge-cligit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWhat 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 | $0.00047 | $0.01355 |
| Opus 5 | $0.00023 | $0.00678 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
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.
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-rolledargvslicing.--helpand--versionalways work and exit0; 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 exit0on 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 | otherstays clean). Read stdin when piped / when the input arg is-. Offer a--json(or--quiet) mode for scripting. Respect non-TTY andNO_COLOR: no colors, spinners, or interactive prompts when output is piped orstdinis not a terminal. Don't crash onSIGPIPE/broken pipe (headclosing 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-runto 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.
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.
- yesterday First seen · 41 lines · 47 tokens per session scan A 75bf2be89200
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.
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.
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…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
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…
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.
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…