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 skills/pariyar07/ariadne/validatornpx skills add pariyar07/ariadne --skill validatorgit clone --depth 1 https://github.com/pariyar07/ariadneWrote 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/skills/pariyar07/ariadne/validator)<a href="https://agentmods.dev/skills/pariyar07/ariadne/validator"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/validator.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 | $0.00046 | $0.02130 |
| Opus 5 | $0.00023 | $0.01065 |
| Sonnet 5 | $0.00009 | $0.00426 |
| Haiku 4.5 | $0.00005 | $0.00213 |
Grade A, and why
ariadne:validator 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 4d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ariadne Validator
Use this skill when the user asks whether a Markdown knowledge vault is structurally valid, navigable, connected, or ready for ongoing agent use.
Tool
Run the bundled validator from the vault root:
/path/to/skills/validator/scripts/validate_vault.sh
Or pass an explicit vault path:
/path/to/skills/validator/scripts/validate_vault.sh /path/to/vault
For a subtree or its schema-v1 research pipeline, pass a vault-relative scope:
/path/to/skills/validator/scripts/validate_vault.sh /path/to/vault --scope "Domains/Product"
/path/to/skills/validator/scripts/validate_vault.sh /path/to/vault --scope "Domains/Product" --profile research
Scoped runs still inventory the whole vault before filtering findings. --scope rejects absolute paths, traversal, missing paths, and files. --profile research requires a scope; it keeps in-scope YAML, broken-link, orphan, and unlinked-Base failures while excluding sibling-origin defects. Descriptor, hub, and routing findings carry explicit governing obligations when an outside origin directly applies to the selected scope.
The shell wrapper checks for Node.js and delegates to validate_vault.js.
Scope Topology Synchronizer
Resolve scripts/sync_scope_topology.js relative to this installed skill. It is the only scope topology mutation authority. --check is always zero-write and reports findings, proposed changes, complete content_write_paths, and plan_hash:
node /path/to/skills/validator/scripts/sync_scope_topology.js /path/to/vault --check
node /path/to/skills/validator/scripts/sync_scope_topology.js /path/to/vault --check --scope "Domains/Product"
Mutation accepts one exact schema-v1 JSON request:
{"operation_schema":1,"operation":"move","target_scope_id":"alpha","source_path":"Domains/Alpha","destination_path":"Projects/Alpha","normalize_files":[],"allowed_write_paths":["00 Index.md","Agent/Scope Map.md"]}
node /path/to/skills/validator/scripts/sync_scope_topology.js /path/to/vault --write --request /path/to/request.json
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 266 B
- scripts/scope-topology/findings.js 17 KB runs code
- scripts/scope-topology/index.js 260 B runs code
- scripts/scope-topology/inventory.js 6.6 KB runs code
- scripts/scope-topology/markers.js 2.4 KB runs code
- scripts/scope-topology/model.js 5.7 KB runs code
- scripts/scope-topology/operations.js 31 KB runs code
- scripts/scope-topology/render.js 11 KB runs code
- scripts/scope-topology/schema.js 5.6 KB runs code
- scripts/scope-topology/synchronizer.js 40 KB runs code
- scripts/sync_scope_topology.js 1.6 KB runs code
- scripts/validate_vault.js 49 KB runs code
- scripts/validate_vault.sh 362 B runs code
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/00 Index.md 48 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/00 Projects Index.md 69 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/Alpha/00 Alpha Index.md 116 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/Alpha/AGENTS.md 124 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/Alpha/Deep/00 Deep Index.md 50 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/Alpha/Deep/Bases/00 Bases Index.md 48 B
- test/fixtures/recursive_scopes/arbitrary_depth_child_scope_pass/Projects/Alpha/Deep/Bases/Deep Notes.base 90 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/00 Index.md 150 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/Bases/00 Bases Index.md 122 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/Bases/Master Notes.base 251 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/Domains/00 Domains Index.md 131 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/Domains/Alpha/00 Alpha Index.md 150 B
- test/fixtures/recursive_scopes/base_scope_formula_missing_branch_warning/Domains/Alpha/AGENTS.md 118 B
- test/fixtures/recursive_scopes/canvas_wikilink_target_pass/00 Index.md 132 B
- test/fixtures/recursive_scopes/canvas_wikilink_target_pass/Topology System Map.canvas 33 B
- test/fixtures/recursive_scopes/duplicate_basename_wikilink_ambiguity_warning/00 Index.md 65 B
- test/fixtures/recursive_scopes/duplicate_basename_wikilink_ambiguity_warning/Area1/Shared.md 9 B
- test/fixtures/recursive_scopes/duplicate_basename_wikilink_ambiguity_warning/Area2/Shared.md 9 B
- test/fixtures/recursive_scopes/duplicate_basename_wikilink_ambiguity_warning/Topic.md 65 B
- test/fixtures/recursive_scopes/local_agents_policy_repetition_warning/00 Index.md 82 B
- test/fixtures/recursive_scopes/local_agents_policy_repetition_warning/Teams/Platform/00 Platform Index.md 33 B
- test/fixtures/recursive_scopes/local_agents_policy_repetition_warning/Teams/Platform/AGENTS.md 153 B
- test/fixtures/recursive_scopes/local_base_without_scope_filter_warning/00 Index.md 51 B
- test/fixtures/recursive_scopes/local_base_without_scope_filter_warning/Projects/Gamma/00 Gamma Index.md 30 B
- test/fixtures/recursive_scopes/local_base_without_scope_filter_warning/Projects/Gamma/Bases/00 Bases Index.md 39 B
- test/fixtures/recursive_scopes/local_base_without_scope_filter_warning/Projects/Gamma/Bases/MissingScope.base 47 B
- test/fixtures/recursive_scopes/nested_base_yaml_parsing/00 Index.md 49 B
- test/fixtures/recursive_scopes/nested_base_yaml_parsing/Projects/Beta/00 Beta Index.md 29 B
- test/fixtures/recursive_scopes/nested_base_yaml_parsing/Projects/Beta/Bases/00 Bases Index.md 32 B
- test/fixtures/recursive_scopes/parent_hub_missing_child_link_warning/00 Index.md 48 B
- test/fixtures/recursive_scopes/parent_hub_missing_child_link_warning/Projects/00 Projects Index.md 33 B
- test/fixtures/recursive_scopes/parent_hub_missing_child_link_warning/Projects/Child/00 Child Index.md 139 B
- test/fixtures/recursive_scopes/research_legacy_gated/00 Index.md 38 B
- test/fixtures/recursive_scopes/research_legacy_gated/Domain/Legacy Boundary.md 131 B
- test/fixtures/recursive_scopes/research_legacy_gated/Domain/Uncompiled.md 182 B
- test/fixtures/recursive_scopes/research_schema_valid/00 Index.md 59 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Compiled Hub.md 74 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Compiled Note.md 151 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Inquiry Hub.md 46 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Raw Hub.md 62 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Research Boundary.md 415 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Shared.md 294 B
- test/fixtures/recursive_scopes/research_schema_valid/Domain/Synthesis Hub.md 48 B
- test/fixtures/recursive_scopes/research_schema_valid/Other/Shared.md 31 B
- test/fixtures/recursive_scopes/research_schema_warnings/00 Index.md 40 B
- test/fixtures/recursive_scopes/research_schema_warnings/Domain/Compiled Hub.md 47 B
- test/fixtures/recursive_scopes/research_schema_warnings/Domain/Cycle A.md 153 B
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.
- 4d ago First seen · 160 lines · 46 tokens per session scan A 4bd059f23232
ariadne:validator is a skill published in the GitHub repository pariyar07/ariadne (19 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,130 once invoked, about $0.0002 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 skills, from other repositories
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
gitbook-import
Import a GitBook space (company docs / whitepaper) into the Obsidian vault as well-linked atomic notes + MOC + concept links + RAG reindex — a proven pipeline as one command. Trigger on "/gitbook-import ", "import this gitbook", "gitbook to vault". Thin wrapper over the import engine; idempotent re-import supported.
granola-sync
On-demand pull of fresh calls/meetings from Granola (summaries + transcripts + participants) into the Obsidian vault via the official API. Incremental + idempotent (dedup by note id + updatedat) — safe to re-run, no duplicates. Trigger on "/granola-sync", "pull granola", "refresh meetings".
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
docling
PRIMARY skill for converting .pdf, .docx, .pptx, .xlsx, .doc, .ppt, .xls, images, and audio/video files (.mp3, .wav, .m4a, .mp4, .mov, etc.) to Markdown. Always prefer this over the docx/pdf/pptx/xlsx/paddleocr skills — docling uses GPU-accelerated OCR + layout detection + table structure extraction for documents, and…
meeting-processing
Обработка встреч, расшифровок и заметок: извлечение решений, задач, фактов, рисков и устойчивых знаний с маршрутизацией по структуре хранилища. Перед регулярными встречами с историей использует context-compression, чтобы не читать весь архив встреч целиком.