Borrowing it
Nothing to install: this file belongs to dungnotnull/mountain-landslide-early-warning-agent-skill. 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/dungnotnull/mountain-landslide-early-warning-agent-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/dungnotnull/mountain-landslide-early-warning-agent-skillWrote 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/dungnotnull/mountain-landslide-early-warning-agent-skill/claude-md)<a href="https://agentmods.dev/instructions/dungnotnull/mountain-landslide-early-warning-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/dungnotnull/mountain-landslide-early-warning-agent-skill/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/dungnotnull/mountain-landslide-early-warning-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/dungnotnull/mountain-landslide-early-warning-agent-skill/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 | $0.01405 | $0.01405 |
| Opus 5.5 | $0.00562 | $0.00562 |
| Sonnet 5.5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
mountain-landslide-early-warning-agent-skill 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 2mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Skill 238: mountain-landslide-early-warning
Skill Identity
- Skill Name:
mountain-landslide-early-warning - Tagline: Mountain Landslide Early-Warning Advisor — Landslide Hazard & Early-Warning Engineering analysis & decision-support harness.
- Current Phase: Phase 6 — Production-Grade Runtime (v2.0.0)
- Folder:
D:\972026\238-mountain-landslide-early-warning\ - Version: 2.0.0
What this skill is
This skill provides a structured, evidence-backed analytical workflow for
Landslide Hazard & Early-Warning Engineering. v2.0 adds a bulletproof
Python skill-registry runtime (src/landslide_ews/) alongside the markdown
harness (skills/*.md). The runtime is LLM-agnostic: the deterministic core
(slope stability, rainfall thresholds, knowledge retrieval, language
detection) runs without any model, with graceful fallbacks and explicit
limitation flags when an LLM is unavailable.
Two execution surfaces
- Markdown harness (
skills/*.md) — driven by Claude Code. The 6-step protocol: sub-gather-requirements → sub-evidence-collector → sub-core-analysis → sub-knowledge-updater → sub-advisor → quality gate. - Python runtime (
src/landslide_ews/) — drives the same skills deterministically. Entry point:landslide_ews.runtime.Orchestrator. CLI:python scripts/run_harness.py "..." --slope '{...}'.
Both share the same skill registry, tools, hooks, config, references, and
JSON I/O schemas (assets/schemas/). See SKILL.md for the full contract.
Architecture (v2.0)
config/ type-safe config (YAML + env + feature flags)
skills/ markdown harness (LLM-facing)
src/landslide_ews/
skills/ descriptor / loader / registry / chain-of-thought router
hooks/ lifecycle hooks + event bus (observability + audit trail)
tools/ compute_slope_stability, rainfall_threshold,
knowledge_query, language_detect
runtime/ orchestrator + state machine + deterministic fallback handlers
context.py bounded context window + deterministic compaction
logging.py structured JSON logging
errors.py typed exception hierarchy
references/ prompt templates + domain knowledge + grounding
assets/ JSON I/O schemas + architecture diagram
scripts/ setup_project / seed_knowledge_base / ingest_sources / run_harness
tests/ pytest suite (34 tests) + legacy scenario validator
SKILL.md skill registry documentation
SECOND-KNOWLEDGE-BRAIN.md living knowledge base
tools/knowledge_updater.py crawl pipeline
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.
- 2mo ago First seen · 139 lines · 1,405 tokens per session scan A f540508d34ca
mountain-landslide-early-warning-agent-skill CLAUDE.md is an instructions file published in the GitHub repository dungnotnull/mountain-landslide-early-warning-agent-skill (7 stars, last pushed 3mo ago), licensed MIT. It adds 1,405 tokens to every session, about $0.0056 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 2026-08-31.
mountain-landslide-early-warning-agent-skill CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mountain-landslide-early-warning-agent-skill CLAUDE.mddungnotnull/mountain-landslide-early-warning-agent-skill | Instructions file | 7 | 3mo ago | MIT | A | 1,405 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | 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 |