Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joncovington/MEICAgentnpx agentmods add commands/joncovington/meicagent/paper-loopWrote 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/commands/joncovington/meicagent/paper-loop)<a href="https://agentmods.dev/commands/joncovington/meicagent/paper-loop"><img src="https://agentmods.dev/badge/commands/joncovington/meicagent/paper-loop/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/commands/joncovington/meicagent/paper-loop"><img src="https://agentmods.dev/badge/commands/joncovington/meicagent/paper-loop.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 | $0.00000 | $0.00608 |
| Opus 5.5 | $0.00000 | $0.00243 |
| Sonnet 5.5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
paper-loop 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run one iteration of the MEICAgent parallel-shadow paper-trading loop.
As of the standalone runner, the paper loop is implemented in code (src/paper_loop.py), not agent orchestration — this keeps a single source of truth for the iteration logic. Prefer the unattended daemon (/paper-start) for a full session; use this skill for a single manual iteration (e.g. a one-off force-close pass, or a quick check).
Run one iteration
python src/paper_loop.py --once
This runs, for every symbol in config.json's symbols, one full pass: fetch the live underlying price + IV rank, the shared VIX / VIX1D (→ ratio, → VIX-banded short delta), and GEX; build wing-width candidates from wing_widths_by_symbol; then hand the snapshot to paper.process_symbol, which marks/exits every open paper IC across all four profiles (per-side stops, the settlement-aware force-close cascade with the physically-settled early close + assignment/pin friction, and cash-settled left-to-expire settlement — no profit target) and evaluates new entries per profile. All writes go to data/paper_trades.db; the live account and data/meic_trades.db are never touched.
Report the per-symbol, per-profile outcomes from the JSON it prints (fills, skip reasons, or exits).
Unattended session
For a full session that runs on its own without per-iteration invocation, use /paper-start, which registers a Windows scheduled task running --once every 2 minutes (robust, self-healing, persists across sessions, time-gated to market hours). Manage it directly with:
python src/paper_loop.py --install-task # register + fire the first run (recommended)
python src/paper_loop.py --status # daemon/task status + open-position count
python src/paper_loop.py --uninstall-task # stop the unattended session
python src/paper_loop.py --eod-report # write logs/paper-eod-<date>.md now (--date to backfill)
The daemon also writes that deterministic end-of-day report automatically, once, at the 16:00 settlement pass — a per-profile metrics table (trades, win rate, net P&L, expectancy, profit factor, max drawdown), an exits-by-reason breakdown, and per-symbol P&L. It's code-generated (no agent), distinct from the agent-synthesized /paper-report.
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 · 31 lines · 0 tokens per session scan A 8039d979545f
paper-loop is a command published in the GitHub repository joncovington/MEICAgent (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 608 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.