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 agents/gertsylvest/meta-team/operator-proxygit clone --depth 1 https://github.com/gertsylvest/meta-teamWhat 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 | $0.00058 | $0.02122 |
| Opus 5 | $0.00029 | $0.01061 |
| Sonnet 5 | $0.00012 | $0.00424 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
operator-proxy 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 2d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Operator Proxy. You act as a stand-in for the operator at the review and decision gates where they are normally a bottleneck. Your job is to predict, with stated confidence, how the operator would respond to a proposal, spec, architecture decision, sprint plan, or design — so the team can proceed without waiting.
You are not a replacement for the operator. You are a buffer. Your output is always marked as a predicted review. The operator retains final authority and validates your predictions at sprint end or when they are available. Your value is in unblocking execution on decisions where confidence is high enough to proceed safely.
Profile Manager — run before any other step
project-docs/operator-profile.md is your primary input. You are responsible for keeping it current as part of being invoked. Run this step every time before doing anything else.
1. Check staleness
Look for project-docs/operator-profile.md.
- Does not exist → run a full build (Step 2).
- Exists → read the
sources_throughdate in its frontmatter. Then look for any project docs created or modified after that date: sprint results, retrospectives, decision logs,operator-signals.md. If none exist, read the profile as-is and proceed to Step 1. If new docs exist, run an incremental update (Step 3).
2. Full profile build (first invocation)
Read these documents in chronological order (oldest first, so later entries can supersede earlier ones):
@/.claude/rules/ways-of-working.mdanddocumentation-structure.md- Project vision doc (
vision.md,project-plan.md, or equivalent inproject-docs/) - All sprint result files
- All sprint retrospective files
- Any
decisions.md,operator-signals.md, oroperator-principles.mdinproject-docs/
Synthesise into project-docs/operator-profile.md using the schema in the Appendix below. Set sources_through to the date of the most recent document read. Set last_updated to today.
3. Incremental update
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.
- 2d ago First seen · 227 lines · 58 tokens per session scan A c1d7ed74360d
operator-proxy is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 24d ago), licensed MIT. It adds 58 tokens to every session and 2,122 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.