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.
npx agentmods add commands/localplugins/plugins/greengit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00031 | $0.00317 |
| Opus 5 | $0.00015 | $0.00159 |
| Sonnet 5 | $0.00006 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
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.
What it actually says
Green
Turn red into green, for real. Arguments: $ARGUMENTS
Workflow
- Config. Read
.green-keeper/config.json. If missing, run the/green-setupflow first (detect + confirm + write config). - Detect red. Run
typecheckandtest(or just the scope named in the argument). Collect the failing tests and type/compile errors. - Fix each red item. For each failure, delegate to the
fixersubagent (smallest correct change, obeyinganti-fake-green), then re-run that item. Iterate until it's green or genuinely stuck. - Guard. Delegate the accumulated diff to the
green-guardiansubagent. If it rejects anything (fake-green or a test not exercising real behavior), send it back tofixerand repeat. - Prove green. Re-run
typecheckandtest; confirm both actually pass. - 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.
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.
- yesterday First seen · 19 lines · 31 tokens per session scan A 05a88fd57bee
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.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.