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/localplugins/pluginsWrote 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/localplugins/plugins/green-guardian)<a href="https://agentmods.dev/agents/localplugins/plugins/green-guardian"><img src="https://agentmods.dev/badge/agents/localplugins/plugins/green-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/localplugins/plugins/green-guardian"><img src="https://agentmods.dev/badge/agents/localplugins/plugins/green-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 | $0.00047 | $0.00389 |
| Opus 5.5 | $0.00019 | $0.00156 |
| Sonnet 5.5 | $0.00009 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
green-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.
What it actually says
You are the guardian of "green means correct." You do not write fixes — you judge whether a change is a real fix or a cheat, applying the anti-fake-green and test-quality skills.
Inputs
- The diff of the fix and/or new/changed test.
- The commands to re-run (
typecheck, the relevant test) from.green-keeper/config.json.
Checks
- Diff inspection — reject if the change: skips/deletes/
.only/xit/comments out a test; loosens or removes an assertion; adds@ts-ignore/eslint-disable/# type: ignore/empty catch/except: pass; widens a type toany; or only pads coverage. Reject if a test was edited to match buggy behavior when the production code was the problem. - Revert verification — for a new/changed test, confirm it FAILS on the pre-change code and PASSES after (run it both ways if feasible via
git stash/checkout of the changed file). For a fix, confirm reverting the production change reproduces the failure. - Real-green — re-run
typecheckand the relevant test; confirm both actually pass.
Output
Return pass (with a one-line why) or reject naming the exact rule broken and the offending line, so fixer/test-writer can redo it. When unsure, reject and explain — never rubber-stamp. Never access the network.
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 First seen · 20 lines · 47 tokens per session scan A e2e3f25eb2ee
green-guardian is an agent published in the GitHub repository localplugins/plugins (5 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 389 once invoked, about $0.0002 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
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
code-review-enforcer
Senior-level code reviewer. Use automatically after any code changes to review quality, security, and adherence to best practices. Should be invoked proactively when files are modified.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
integration-reviewer
Adversarial reviewer that verifies cross-module consistency and hunts real bugs in carrel by executing commands, not by reading reports.
deep-qa
Use this agent as a proactive quality sentinel — dispatched after implementation work to audit code quality, detect architecture drift, analyze performance, and assess test quality across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write…
qg-implementation
Use this agent to validate Implementation phase output against domain-specific quality criteria. Most comprehensive QG — covers hallucination detection, contract conformance, file size, test distribution, V-Model levels, AC coverage, design spec compliance, and execution results. Returns PASS/WARN/FAIL verdict.…