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 workspace-instructionsgit 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/workspace-instructions)<a href="https://agentmods.dev/skills/pariyar07/ariadne/workspace-instructions"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/workspace-instructions/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/workspace-instructions"><img src="https://agentmods.dev/badge/skills/pariyar07/ariadne/workspace-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 124 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.05124 |
| Opus 5 | $0.00049 | $0.02562 |
| Sonnet 5 | $0.00020 | $0.01025 |
| Haiku 4.5 | $0.00010 | $0.00512 |
Grade A, and why
ariadne:workspace-instructions 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 9d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ariadne Workspace Instructions
Use this skill to make a workspace agent-readable and connect it to Ariadne vault context when useful.
This skill owns workspace-level instruction files. ariadne:global-discovery owns machine-level registry files and global adapter blocks.
Core Model
Workspace instruction files are a bridge:
global agent files -> registered vault discovery -> vault or scope context
workspace instruction files -> local workspace rules -> optional vault/scope link
Keep the bridge small. Do not copy vault navigation, private absolute paths, or long scope notes into public workspace files.
Bounded Discovery
Inspect only the smallest useful workspace context:
- Current directory and parents up to the nearest workspace root.
- Existing
AGENTS.md,CLAUDE.md,GEMINI.md,WORKSPACE.md, and local override files in that root. .gitignore.- High-signal workspace files such as
README.md, package or build manifests, test config, and existing docs indexes. - Git state when relevant: whether the folder is inside a worktree, the repository root, tracked instruction files, ignored local files, and whether remotes suggest the workspace is shared.
- Registered vault metadata only when the user asks to connect the workspace to Ariadne context, repair stale global discovery, or the prompt is ambiguous about which known workspace/vault it refers to.
Do not scan the whole computer. Do not scan an entire vault or repository to infer intent. Use filenames, manifests, and existing entry files first.
Mechanical Signal Check
When the workspace shape is uncertain, or when repairing existing instruction files, you may run the deterministic checker:
node scripts/check_workspace.js "/path/to/workspace" --json
node scripts/check_workspace.js "/path/to/workspace" --json --vault "/confirmed/path/to/vault"
Resolve scripts/check_workspace.js relative to this SKILL.md. In an Ariadne repository checkout, the same script lives at skills/workspace-instructions/scripts/check_workspace.js.
What ships with it
46 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 223 B
- references/instruction-file-rules.md 6.3 KB
- references/workspace-instruction-files.md 16 KB
- references/workspace-instruction-scenarios.md 13 KB
- scripts/check_workspace.js 27 KB runs code
- test/fixtures/adapter_duplicate_normalization/scenario.json 891 B
- test/fixtures/agents_missing_command_guidance/scenario.json 685 B
- test/fixtures/agents_oversized_for_standard/scenario.json 7.6 KB
- test/fixtures/child_git_repo_traversal_boundary/scenario.json 1.2 KB
- test/fixtures/codex_override_in_sync/scenario.json 930 B
- test/fixtures/codex_override_out_of_sync/scenario.json 958 B
- test/fixtures/copied_global_discovery_block/scenario.json 692 B
- test/fixtures/current_research_skill_names/scenario.json 821 B
- test/fixtures/duplicate_current_markers_stop/scenario.json 753 B
- test/fixtures/foreign_markers_preserved/scenario.json 677 B
- test/fixtures/git_shared_clean/scenario.json 1.2 KB
- test/fixtures/git_worktree_root/scenario.json 519 B
- test/fixtures/hermes_agents_direct_default/scenario.json 725 B
- test/fixtures/hermes_both_context_files/scenario.json 1.0 KB
- test/fixtures/hermes_context_shadows_agents/scenario.json 914 B
- test/fixtures/hermes_discusses_agents_import/scenario.json 894 B
- test/fixtures/hermes_private_path_leakage/scenario.json 878 B
- test/fixtures/hermes_unsupported_agents_import/scenario.json 892 B
- test/fixtures/legacy_marker_migrate_in_place/scenario.json 680 B
- test/fixtures/local_only_missing_gitignore/scenario.json 871 B
- test/fixtures/macos_private_path_leakage/scenario.json 548 B
- test/fixtures/malformed_marker_stop/scenario.json 605 B
- test/fixtures/multiple_plausible_vaults_ask/scenario.json 677 B
- test/fixtures/nested_subproject_instructions/scenario.json 780 B
- test/fixtures/non_git_portable_private_path/scenario.json 359 B
- test/fixtures/private_path_leakage_split/scenario.json 745 B
- test/fixtures/retired_research_skill_names/scenario.json 895 B
- test/fixtures/scope_identity_colliding_descriptor/scenario.json 1.8 KB
- test/fixtures/scope_identity_current/scenario.json 1.1 KB
- test/fixtures/scope_identity_duplicate_id/scenario.json 1.3 KB
- test/fixtures/scope_identity_invalid/scenario.json 1.8 KB
- test/fixtures/scope_identity_partial/scenario.json 1.4 KB
- test/fixtures/scope_identity_stale_path/scenario.json 1.1 KB
- test/fixtures/scope_identity_unknown/scenario.json 884 B
- test/fixtures/scope_identity_unverified/scenario.json 713 B
- test/fixtures/vault_navigation_bloat/scenario.json 1.4 KB
- test/fixtures/workspace_duplicate_child_mentions/scenario.json 1.3 KB
- test/fixtures/workspace_parent_pre_migration/scenario.json 1.4 KB
- test/fixtures/workspace_reference_missing/scenario.json 724 B
- test/fixtures/workspace_root_git_with_child_repos/scenario.json 1.3 KB
- test/test_workspace_instructions.js 8.4 KB runs code
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.
- 9d ago First seen · 228 lines · 99 tokens per session scan A d1c2ab988f48
ariadne:workspace-instructions is a skill published in the GitHub repository pariyar07/ariadne (20 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 5,124 once invoked, about $0.0005 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.