green

A command that finds failing tests and type or compile errors, fixes their underlying causes, and runs the checks again until they pass or a real decision is needed.

In plain words
What is it for?
Use it after code changes to diagnose failures, apply minimal corrections, verify tests and types, and review that the result is genuine.
Why use it?
It turns failed checks into verified fixes without hiding errors or weakening tests.

Command

Install

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.

agentmods
npx agentmods add commands/localplugins/plugins/green
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00317
Opus 5 $0.00015 $0.00159
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured yesterday against content hash 05a88fd57bee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

green 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 yesterday.

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.

green-keeper/commands/green.md · 19 lines

What it actually says

Green

Turn red into green, for real. Arguments: $ARGUMENTS

Workflow

  1. Config. Read .green-keeper/config.json. If missing, run the /green-setup flow first (detect + confirm + write config).
  2. Detect red. Run typecheck and test (or just the scope named in the argument). Collect the failing tests and type/compile errors.
  3. Fix each red item. For each failure, delegate to the fixer subagent (smallest correct change, obeying anti-fake-green), then re-run that item. Iterate until it's green or genuinely stuck.
  4. Guard. Delegate the accumulated diff to the green-guardian subagent. If it rejects anything (fake-green or a test not exercising real behavior), send it back to fixer and repeat.
  5. Prove green. Re-run typecheck and test; confirm both actually pass.
  6. Report. Summarize each root cause and the minimal fix. If anything remains red because it needs a human/product decision, say so plainly — never fake it.

Never weaken/skip a test or silence an error to pass. Never access the network.

Changes

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.

  1. yesterday First seen · 19 lines · 31 tokens per session scan A 05a88fd57bee

Subscribe to this mod's changes

green is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 317 once invoked, about $0.0002 per session on Opus 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.