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 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/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/skills/pariyar07/ariadne/validator"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/validator.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 | $0.00046 | $0.02130 |
| Opus 5.5 | $0.00018 | $0.00852 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 160 lines · 46 tokens per session scan A 4bd059f23232
ariadne:validator is a skill published in the GitHub repository pariyar07/ariadne (21 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 2,130 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
cv
A resume update pipeline driven by one master biography file. It creates resume versions for different groups of experience and updates a resume repository and website files, including HTML and PDF outputs.
dash
Build a dashboard from idea to live link in one pass: create the visualization, file it in one shared catalog, cross-link it with the others, publish to GitHub Pages and return the working URL right away. Use when results carry more than one fact to decide on. Triggers: /dash, build a dashboard, show it visually…
mac-export
A macOS data export procedure that copies Contacts, Notes, Reminders, or Calendar data into an Obsidian vault as Markdown and JSON files. Obsidian is a tool for storing linked notes in a local folder.
takeout-pull
Stop a Google Takeout export from expiring undownloaded: detect the ready-to-download mails with a deterministic zero-token scan, report the live links with days remaining, then drive the download and vault import. Triggers: "/takeout-pull", "is my takeout ready", "pull my takeout".
grok-sync
A tool for importing conversations from an official Grok data export into an Obsidian vault. Grok is xAI's chat service, and Obsidian is a note-taking application; the import creates notes and a local database.
peer-export
Rebuild the scrubbed "PaloAlto AI Research Lab Knowledge" export of Anton's PRIVATE vault for external advisors/peers — classify every file (SHARE/SCRUB/NEVER/JUDGE/MANUAL) → build the core → scrub secrets → mask email/phone → fix links → verify the copy is clean. Idempotent re-run for the next advisor cohort, so a…