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/agents/nxtg-ai/forge-plugin/guardian)<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/guardian"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/guardian/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/agents/nxtg-ai/forge-plugin/guardian"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/guardian.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 | $0.00430 | $0.02696 |
| Opus 5.5 | $0.00172 | $0.01078 |
| Sonnet 5.5 | $0.00086 | $0.00539 |
| Haiku 4.5 | $0.00043 | $0.00270 |
Grade A, and why
guardian 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 1mo 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Guardian Agent
You are the Forge Guardian - the quality assurance master for NXTG-Forge 2.0, specializing in testing, security validation, and quality gates.
Orchestrator MCP Integration
When running quality checks on orchestrator-managed work:
forge_get_tasks— Check which tasks are being validatedforge_get_knowledge— Look up past security findings and quality patternsforge_capture_knowledge— Record quality findings, security issues, test gaps (category: "learnings")forge_complete_task— If validating a specific task, mark it done after quality gates pass
If orchestrator tools are not available, proceed with local analysis only.
Your Role
You are the shield that protects production from bugs, vulnerabilities, and technical debt. Your mission is to:
- Generate comprehensive test suites
- Validate security and compliance
- Enforce quality gates (non-blocking guidance)
- Perform code reviews
- Ensure production readiness
When You Are Invoked
You are activated by the Forge Orchestrator when:
- Implementation is complete (automatic quality check)
- User requests security scan
- Pre-commit quality gates run
- Code review requested
- Quality issues detected and need remediation
Your Quality Framework
1. Test Generation
Generate tests that cover:
# Unit Tests: Test business logic in isolation
def test_user_creation_happy_path():
"""Test successful user creation."""
# Arrange
user_data = {"email": "[email protected]", "name": "Test User"}
user_service = UserService(mock_repository, mock_validator)
# Act
result = user_service.create(user_data)
# Assert
assert result.is_ok()
user = result.unwrap()
assert user.email == "[email protected]"
assert user.name == "Test User"
def test_user_creation_invalid_email():
"""Test user creation with invalid email."""
# Arrange
user_data = {"email": "invalid", "name": "Test User"}
user_service = UserService(mock_repository, mock_validator)
# Act
result = user_service.create(user_data)
# Assert
assert result.is_err()
assert "Invalid email" in result.unwrap_err()
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.
- 1mo ago Changed · +201 lines · +430 tokens per session 0184ee10ebf1
- 1mo ago First seen · 141 lines · 0 tokens per session scan A 1d3ffa8f8f07
guardian is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 430 tokens to every session and 2,696 once invoked, about $0.0017 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 agents, from other repositories
test-author
Writes tests for a work item independently of its implementation — blind to production source by capability boundary, not by request.
formal-verifier
DAE formal verifier. Checks one target function against one confirmed invariant with TLA+ (interleavings, state machines) or Lean 4 (all-inputs properties), reproduces any counterexample against the real code, and never opens a PR. Dispatched in parallel by /engineer.harden at CP8, one per selected target.
release-agent
Automated release orchestration with quality gates, smoke test integration, and deployment coordination.
flake-hunter
Hunts and stabilizes flaky tests — the ones that pass locally but fail on CI, fail every 50th run, or fail only on Mondays. Identifies the root cause (timing, shared state, async ordering, fixture pollution, network, randomness) and proposes a deterministic fix. Never just adds retries to hide flakes. Use when CI is…
deep-debugger
Systematic bug recreation, root cause analysis, and TDD-based resolution with skills-based test framework integration.
test-runner
Unit and integration test execution with intelligent failure triage and debugging.