Borrowing it
Nothing to install: this file belongs to kostadis/CampaignGenerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kostadis/CampaignGenerator/main/CLAUDE.mdgit clone --depth 1 https://github.com/kostadis/CampaignGeneratorWrote 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/kostadis/campaigngenerator/claude-md)<a href="https://agentmods.dev/instructions/kostadis/campaigngenerator/claude-md"><img src="https://agentmods.dev/badge/instructions/kostadis/campaigngenerator/claude-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.
<a href="https://agentmods.dev/instructions/kostadis/campaigngenerator/claude-md"><img src="https://agentmods.dev/badge/instructions/kostadis/campaigngenerator/claude-md.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 | $0.08042 | $0.08042 |
| Opus 5.5 | $0.03217 | $0.03217 |
| Sonnet 5.5 | $0.01608 | $0.01608 |
| Haiku 4.5 | $0.00804 | $0.00804 |
Grade B, and why
CampaignGenerator CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
MemPalace memory-search policy (search-first for past work/decisions, mining freshness, grep fallback) lives in the same global `~/.claude/CLAUDE.md` under "MemPalace Memory Search" — no repo-specific override here. How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repo.
Codebase search policy (structural queries, non-code fallback, stale-index handling) lives in the global ~/.claude/CLAUDE.md under "Codebase Semantic Search (codebase-memory-mcp)" — no repo-specific override here.
MemPalace memory-search policy (search-first for past work/decisions, mining freshness, grep fallback) lives in the same global ~/.claude/CLAUDE.md under "MemPalace Memory Search" — no repo-specific override here.
CampaignGenerator
A D&D session-prep CLI that assembles campaign documents and session beats, calls the Claude API to generate encounter/narration documents, and integrates with rpglib + MemPalace for verbatim retrieval from a local RPG library.
Project structure
# ── Web UI ──
startup # Launch script — builds frontend, starts FastAPI server
server/ # FastAPI backend (routers, subprocess SSE streaming)
frontend/ # Vue 3 + TypeScript + Pinia + Vue Router
# ── CLI tools ──
campaignlib.py # Shared library — all scripts import from here
pipelines/session_prep/prep.py # CLI: session beat / session arc prep
session_doc/sd_consistency.py # CLI: Pass 1 — consistency check (sd_*.py replaced session_doc.py)
session_doc/sd_plan.py # CLI: Pass 3 — narrative plan
session_doc/sd_narrate.py # CLI: Pass 5 — per-scene narration
session_doc/sd_corrections.py # CLI: generate *.transcript.cleaned.vtt from the raw
# tape + transcript_corrections.yaml (#250 R4)
session_doc/ # Post-session pipeline CLIs (sd_*, assemble, scene_extract,
# enhance_summary, …) + shared helpers (io, voice,
# roster, examples, narrate)
server/migrate_session_doc.py # CLI: one-shot ui_state.yaml → session_doc.yaml — python -m server.migrate_session_doc --campaign-dir /path/to/campaign
server/migrate_ensemble_config.py # CLI: one-shot ui.ensemble → ensemble.yaml — python -m server.migrate_ensemble_config --campaign-dir /path/to/campaign
server/migrate_narrate_genre.py # CLI: one-shot narrate.genre (a paste) → paths.genre_file (a path) — python -m server.migrate_narrate_genre --campaign-dir /path/to/campaign
pipelines/grounding/npc_table.py # CLI: generate NPC reference table
pipelines/grounding/distill.py # CLI: convert summaries → world_state.md
pipelines/grounding/campaign_state.py # CLI: generate completed-content grounding doc
pipelines/grounding/make_tracking.py # CLI: extract trackable events from a module
pipelines/grounding/thread_registry.py # CLI: narrative-thread canon — propose (harvest),
# ratify (atomic accept), rule, add/log/set-status/alias,
# list/proposals/check --json. Surfaced at /grounding/threads
pipelines/rlm/query.py # CLI: search summaries
pipelines/grounding/planning.py # CLI: NPC dossiers + arc scores → planning.md
pipelines/grounding/party.py # CLI: character sheets + summaries → party.md
pipelines/summary_native/ # CLI: summary_native — validate | build | synth | compare; grounding-doc drafts straight from reviewed structured summaries
pipelines/content_ingest/dnd_sheet.py # CLI: D&D Beyond PDF → markdown (vision API)
pipelines/workspace/new_workspace.py # CLI: create a new campaign workspace
pipelines/session_prep/transform.py # CLI: NotebookLLM dossiers → prep input
# ── RLM tools ──
pipelines/rlm/rpg_retriever.py # Tiered retrieval (drawer / statblock / cost-tagged candidate)
pipelines/rlm/fivetools_catalog.py # Mtime-cached name index over canonical 5etools data
pipelines/rlm/dossier_proposer.py # Run retrieval → write docs/dossier_proposal.md
pipelines/rlm/proposal_loader.py # Render pipelines consume approved proposals
pipelines/rlm/mempalace_client.py # Writes via MemPalace MCP
pipelines/rlm/mcp_server.py # MCP tools: rpg_search, propose_dossier, suggest_conversion
pipelines/content_ingest/convert_book.py # PDF → 5etools JSON (pdf-translators)
pipelines/content_ingest/fivetools_ingest.py # 5etools JSON → MemPalace drawers
pipelines/rlm/resolve_refs.py # Resolve refs.yaml + refs.local.yaml → concrete JSON paths
pipelines/rlm/launch_5etools_mcp.py # Per-campaign 5etools MCP server launcher (reads refs.yaml)
# ── Config & docs ──
config/
config.yaml # Default paths to documents and agent prompts
system_prompt.md # Single-mode system prompt
agents/ # Pipeline-mode prompts (lore_oracle, encounter_architect, voice_keeper)
docs/ # Default doc location (override via config)
campaign_state.md, world_state.md, mechanics.md, planning.md, party.md
logs/ # Auto-generated timestamped session logs
tests/test_prep.py # Tests for campaignlib, prep, and session_doc logic
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 Changed · +2 lines · +122 tokens per session 11de2b709e20
- 5d ago First seen · 404 lines · 7,920 tokens per session scan B e44af79c6c61
CampaignGenerator CLAUDE.md is an instructions file published in the GitHub repository kostadis/CampaignGenerator (5 stars, last pushed 2d ago), licensed MIT. It adds 8,042 tokens to every session, about $0.0322 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.