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 research-ingestgit 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/research-ingest)<a href="https://agentmods.dev/skills/pariyar07/ariadne/research-ingest"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/research-ingest/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/research-ingest"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/research-ingest.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 | $0.00053 | $0.00760 |
| Opus 5 | $0.00026 | $0.00380 |
| Sonnet 5 | $0.00011 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
ariadne:research-ingest 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ariadne Research Ingest
Orchestrate one research input without taking over compilation or synthesis ownership. No write begins until the research target and a closed write set are explicit.
Authorization Gate
- Read applicable instructions from the vault root through every ancestor scope to the candidate target. Read root and local indexes, agent navigation, routing matrices, and the candidate research hub or boundary descriptor progressively.
- Discover candidate scopes and descriptors read-only. Do not scan the whole vault by default.
- In a multi-scope vault, require a current-turn named or confirmed target scope. A search hit, one likely match, an existing card, prior conversation, current directory, or active skill is not confirmation.
- Construct and state
allowed_write_setbefore any mutation. Include the target subtree plus each individually named parent hub, routing matrix, root Base formula, or other external file required for discoverability. An unnamed parent or root file is outside the set even when the edit seems minimal. - If the target is missing or ambiguous, ask one short target question and stop before writing. If another required path appears later, extend the write set only after explicit confirmation; otherwise defer it.
Classify The Input
Record its real source_type and one evidence role: external-evidence, first-party-evidence, context, hypothesis, generated-analysis, or derivative-copy.
Use derived_from for upstream provenance. Generated analysis and derivative copies require upstream links and never count as independent corroboration. Preserve chats, observations, hypotheses, and human notes as their actual epistemic role. Do not invent an inquiry solely to complete metadata; use inquiry_links: [] until one is known.
Inspect pipeline readiness through the boundary descriptor and local hubs. A supported descriptor has type: research-boundary, research_schema, a stable boundary_id, scope_path, and path-qualified canonical hub links. If repeatable topology is missing, invoke ariadne:research-pipeline only within the confirmed write set. Do not silently adopt a legacy pipeline.
What ships with it
1 file 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.
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.
- 10d ago First seen · 52 lines · 53 tokens per session scan A 5dafeecec3a1
ariadne:research-ingest is a skill published in the GitHub repository pariyar07/ariadne (20 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 760 once invoked, about $0.0003 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
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
loop-engineering
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
anthropic-os
Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.