Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nxtg-ai/forge-plugin/plugin install nxtg-forgeWrote 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/commands/nxtg-ai/forge-plugin/gap-analysis)<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/gap-analysis"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/gap-analysis/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/commands/nxtg-ai/forge-plugin/gap-analysis"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/gap-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.02842 |
| Opus 5.5 | $0.00008 | $0.01137 |
| Sonnet 5.5 | $0.00004 | $0.00568 |
| Haiku 4.5 | $0.00002 | $0.00284 |
Grade A, and why
gap-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NXTG-Forge Gap Analysis
Optional convenience. No accuracy claim. This is a structured review prompt. It finds what the model finds when it reads the project, and nothing more. On two deliberately seeded public cases (forge-done-fixture, forge-done-fixture-2), a plain review prompt found the same defects at roughly a third to a quarter of this command's cost (fixtures 1 and 2, 24 runs). A clean report is not evidence that nothing is wrong.
You are the Gap Analyst - review the project for missing tests, documentation gaps, security issues, architecture problems, and technical debt. Report what you looked at and what you did not look at.
The five dimensions (computed by code, already run)
!node "${CLAUDE_PLUGIN_ROOT}/scripts/gap-report.mjs"
The output above is the block between <!-- forge-required: gap-analysis v1 --> and <!-- /forge-required -->, computed by scripts/gap-report.mjs. It ran fixed checks for the five dimensions (Testing, Documentation, Security, Architecture, Performance). Each row holds a finding or "nothing found", and at least one recommendation follows. These are fixed checks: they find what they look for and nothing else.
Start your reply with that block, printed exactly as given: every line, in order, as real markdown (not in a code block). You may leave out the two marker comments. Do not reword, reorder, regroup (for example by severity) or skip any line. A Stop check compares your reply with the block line by line; the turn cannot end until every line is there. Your own review, below, comes after the block and never replaces it.
If the output above is empty or has no <!-- forge-required: gap-analysis v1 --> block (the step did not run), print exactly ◌ **Gap checks unavailable** — the check step did not run first.
Your review (after the block)
Everything below is your own review of the project. It follows the computed block, adds what the fixed checks cannot see, and carries no accuracy claim. Label it ## Review (model, no accuracy claim).
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.
- 6d ago Changed · +5 lines · +9 tokens per session 679e7d92d865
- 12d ago Changed df3a12acecb0
- 1mo ago Changed · +189 lines · +12 tokens per session f7508eaacfe8
- 1mo ago First seen · 138 lines · 0 tokens per session scan A bfb58617f81b
gap-analysis is a command published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 2,842 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
investigate
Establish the proven causal chain for the target — from the observed symptom to the root cause that actually explains it — and write a report a fixer or planner can act on without repeating your work. You change nothing and fix nothing: the repository must be exactly as you found it when you finish. No one watches the…
maintainer-review-error-handling
Review the PR for error-handling correctness — surfaced errors, no silent swallows, consistent error patterns (Pi-tuned).
review-errors
Find either defect: a real failure crosses the changed code and becomes indistinguishable from success to the caller, operator, or user who must react; or it escapes its owning item and aborts independent work. Not every error needs logging; recovery is correct when the contract permits it and the right owner can…
classify-red
The project's gate ran and at least one check failed. $ARTIFACTSDIR/validation.md is the record: every check that ran, its group, its exit status, each failing check's output tail, and the path of each check's full output log. Decide why the failed checks failed, judging every one the record names. You fix nothing and…
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…