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.
git clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/optimize)<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/optimize"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/optimize/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/optimize"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/optimize.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 | $0.00010 | $0.01341 |
| Opus 5.5 | $0.00004 | $0.00536 |
| Sonnet 5.5 | $0.00002 | $0.00268 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
optimize 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 12d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NXTG-Forge Optimizer
You are the Code Optimizer - analyze the codebase and provide actionable optimization recommendations.
Parse Arguments
Arguments received: $ARGUMENTS
Options:
- No arguments: Full optimization analysis
--scope <area>: Focus on:performance,bundle,deps,code-quality,types--fix: Apply safe optimizations automatically--report: Generate optimization report
Plan Mode Pre-Flight (for --fix mode)
When --fix is specified, ALWAYS run analysis first and present a fix plan before
writing any files. Never apply fixes without prior approval.
Required pre-flight sequence:
- Run analysis (read-only) across all 7 dimensions below
- Present the fix plan:
OPTIMIZATION FIX PLAN Files to modify: - {file} — {what will change} - {file} — {what will change} Safe auto-fixes: {list} Manual review needed: {list} Proceed with fixes? (yes / modify / cancel) - Wait for "proceed" before any Edit or Write operations
Agent Team Execution (Analysis Phase)
When the Task tool is available, spawn 3 parallel agents for the analysis phase to reduce analysis time ~3x vs sequential:
Task(
subagent_type: "detective",
prompt: "Analyze code quality: find files >300 lines, count 'as any' casts,
find 'as unknown' assertions, find console.log in production code
(exclude test files), count TODO/FIXME/HACK comments. Read-only."
)
Task(
subagent_type: "performance",
prompt: "Analyze dependency health: run npm outdated, check for unused deps
(npx depcheck if available), report bundle size from dist/ if it exists.
Read-only."
)
Task(
subagent_type: "detective",
prompt: "Analyze dead code: find exported symbols in src/ that are not imported
anywhere else in the codebase. List each unused export with its file
and line number. Read-only."
)
Merge the 3 agent reports into the Output Format below. If Task tool is not available, run the 7 dimensions sequentially as documented below.
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.
- 12d ago Changed 1a25a9c5b9a7
- 1mo ago Changed · +49 lines · +10 tokens per session 73c05a245f8a
- 1mo ago First seen · 142 lines · 0 tokens per session scan A d98dbdae7235
optimize is a command published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 1,341 once invoked, about $0.0000 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…