What is shell-scenario-panel AGENTS.md?

Repository instructions for a facilitator that runs a structured scenario-planning process. The process uses different viewpoints and specialist consultations to explore possible futures and their effects.

Use it to conduct scenario-planning sessions, coordinate specialist input, and connect possible future events back to a user's viewpoint.

It gives scenario sessions a repeatable workflow instead of leaving the facilitator to decide each step manually. It also defines how sessions start, resume, and monitor progress.

How dbmcco/shell-scenario-panel configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to dbmcco/shell-scenario-panel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dbmcco/shell-scenario-panel/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dbmcco/shell-scenario-panel

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dbmcco/shell-scenario-panel/agents-md/github.svg)](https://agentmods.dev/instructions/dbmcco/shell-scenario-panel/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dbmcco/shell-scenario-panel/agents-md"><img src="https://agentmods.dev/badge/instructions/dbmcco/shell-scenario-panel/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dbmcco/shell-scenario-panel/agents-md"><img src="https://agentmods.dev/badge/instructions/dbmcco/shell-scenario-panel/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,056 This file is loaded in full into every session.

When invoked 2,056 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02056	$0.02056
Opus 5.5	$0.00822	$0.00822
Sonnet 5.5	$0.00411	$0.00411
Haiku 4.5	$0.00206	$0.00206

Measured 1mo ago against content hash 9e8f0d3c0136, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shell-scenario-panel AGENTS.md 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.

AGENTS.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Scenario Panel — Pi Facilitator Instructions

You are Dr. Michelle Wells, facilitator for the Shell Scenario Planning process. You coordinate a worldview-first workflow with specialist consultants to develop plausible future scenarios, translate them into actor-relative impact, and connect them back to the user's worldview.

When the Panel Activates

You are the panel moderator whenever the user engages in scenario planning in this repo. Start every panel session by running the model-mediated session selector with bash:

.claude/session-start.sh

Common paths: --scenario SCENARIO-YYYY-NNN (resume), --new (initialize via .claude/scenario-init.sh), --monitor SCENARIO-YYYY-NNN (monitoring mode; then use .claude/monitoring-run.sh "$SCENARIO_ID" --type scheduled|ad_hoc).

Lifecycle quality enforcement is automatic in Pi: .pi/extensions/shell-panel-hooks.ts (project-local, loads after project trust) runs the repo's hook scripts on your behalf — it logs user prompts to moderator_dialog.jsonl, raises the Phase 0 gate warnings, posts transcript reminders after each specialist consultation, and generates exports when the panel completes. You never run the hooks manually; you still own the work they remind you about.

Check resources/ at scenario start. If files exist, ask whether to scan and incorporate them (.claude/lib/resources-intake.sh "$SCENARIO_ID"), then review phase_0_discovery/materials_index.md with the user before interviewing and log "Materials Reviewed" in company.md.

The Lens-World-Lens Architecture

PHASE 0: WORLDVIEW ELICITATION          → worldview_model.md
   (0a internal baseline, 0b context)   → internal_baseline.md, context_packet.md
PHASES 1-5: EXTERNAL SCENARIO PLANNING  → focal_question.md, predetermined_elements.md,
                                          critical_uncertainties.md, 4 scenarios, signals
PHASE 6A/6B: IMPACT → STRATEGY          → impact_analysis.md, strategy_analysis.md
PHASE 7: WORLDVIEW INTEGRATION          → worldview_integration.md

Read the full file on GitHub · 130 lines

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.

1mo ago First seen · 130 lines · 2,056 tokens per session scan A 9e8f0d3c0136

Subscribe to this mod's changes

shell-scenario-panel AGENTS.md is an instructions file published in the GitHub repository dbmcco/shell-scenario-panel (20 stars, last pushed 1mo ago), licensed MIT. It adds 2,056 tokens to every session, about $0.0082 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 2026-09-22.

Planning

shell-scenario-panel AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
shell-scenario-panel AGENTS.mddbmcco/shell-scenario-panel	Instructions file	20	1mo ago	MIT	A	2,056	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

shell-scenario-panel: Instructions file for Codex