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 commands/nxtg-ai/forge-plugin/specgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01152 |
| Opus 5 | $0.00000 | $0.00576 |
| Sonnet 5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
spec 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:spec
Generate a comprehensive technical specification for a feature by analyzing your codebase and producing a structured plan with requirements, architecture, implementation steps, and test cases.
| Level | L1 Vibe Coder |
| Category | Feature Development |
| Syntax | /forge:spec [feature name or description] [--interactive] [--output <file>] |
What It Does
/forge:spec is the planning-only counterpart to /forge:feature. It analyzes your existing codebase -- directory structure, code patterns, test conventions, and available dependencies -- then produces a structured specification document covering requirements (functional and non-functional), architecture (components, data models, integration points), implementation plan (files to create, files to modify, ordered steps), testing strategy (unit tests, integration tests, edge cases), and acceptance criteria.
The spec is grounded in your actual code. Instead of producing a generic template, Forge reads your existing implementations via Glob and Grep to understand naming conventions, module organization, and testing patterns. The resulting spec follows those patterns so that implementation feels natural, not foreign.
Without this command, writing a spec means manually surveying the codebase, documenting the plan in a separate file, and hoping you did not miss an integration point. /forge:spec automates the survey and produces a spec that directly feeds into /forge:feature for implementation.
Syntax & Options
/forge:spec [feature name or description] [--interactive] [--output <file>]
| Option | Description |
|---|---|
feature name |
A short name or description of what to spec. If omitted, the command asks interactively. |
--interactive |
Step-by-step spec building with guided questions about requirements, constraints, and test coverage. |
--output <file> |
Save the spec to a specific file path instead of the default .claude/plans/{slug}-spec.md. |
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 · 115 lines · 0 tokens per session scan A f5d69f569e5f
spec is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,152 tokens. 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 commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
paul:verify
Guide manual user acceptance testing of recently built features.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.