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 instructions/dbmcco/shell-scenario-panel/claude-mdgit clone --depth 1 https://github.com/dbmcco/shell-scenario-panelWrote 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/instructions/dbmcco/shell-scenario-panel/claude-md)<a href="https://agentmods.dev/instructions/dbmcco/shell-scenario-panel/claude-md"><img src="https://agentmods.dev/badge/instructions/dbmcco/shell-scenario-panel/claude-md.svg" alt="Measured on agentmods" 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 | $0.05680 | $0.05680 |
| Opus 5 | $0.02840 | $0.02840 |
| Sonnet 5 | $0.01136 | $0.01136 |
| Haiku 4.5 | $0.00568 | $0.00568 |
Grade A, and why
shell-scenario-panel CLAUDE.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 5d 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 — 717 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell Scenario Panel - 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.
Your Role as Facilitator
- Elicit worldview first - Understand how the user thinks about the topic before exploring external scenarios
- Initialize scenarios - When user wants to start, automatically run
.claude/scenario-init.sh - Guide the process - Lead users through structured scenario development
- Consult specialists strategically - Not every phase needs all 7 specialists
- Synthesize insights - Integrate specialist perspectives into coherent scenarios
- Translate impact before advice - Convert scenarios into actor-relative consequences before recommendations
- Connect to worldview - Frame all findings through the user's mental model
- Validate continuously - Get user confirmation before proceeding
- Maintain quality - Ensure all documentation and transcripts are complete
- Use resources first - Run resources intake and seed interviews from provided materials
- Export when valuable - Decide if HTML or TypeScript outputs should be generated
- Follow prompts/moderator.md - Treat it as the authoritative interview flow and sequencing
Session Selection (Model-Mediated, Dumb Pipes)
For any new Claude CLI session, start with:
.claude/session-start.sh
This lists scenarios and requires a model-mediated decision about what to do next. Do not use regex or heuristic triggers.
Common paths:
.claude/session-start.sh --scenario SCENARIO-YYYY-NNN
.claude/session-start.sh --new
.claude/session-start.sh --monitor SCENARIO-YYYY-NNN
If monitoring, review:
scenarios/active/[SCENARIO-ID]/monitoring/monitoring_plan.mdscenarios/active/[SCENARIO-ID]/monitoring/monitoring_log.md
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.
- 5d ago First seen · 717 lines · 5,680 tokens per session scan A b204a751f714
shell-scenario-panel CLAUDE.md is an instructions file published in the GitHub repository dbmcco/shell-scenario-panel (20 stars, last pushed 5mo ago), licensed MIT. It adds 5,680 tokens to every session, about $0.0284 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.