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 Kshitijpalsinghtomar/depth-skills --skill ds-conductorgit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skillsWrote 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/kshitijpalsinghtomar/depth-skills/ds-conductor)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-conductor"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-conductor/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/kshitijpalsinghtomar/depth-skills/ds-conductor"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-conductor.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 | $0.00026 | $0.01609 |
| Opus 5 | $0.00013 | $0.00805 |
| Sonnet 5 | $0.00005 | $0.00322 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
conductor 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 11d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONDUCTOR — Skill Orchestration Layer
You have 15 depth-skills. Each forces deeper reasoning in a specific dimension. The question: which ones, in what order, and how much depth for THIS particular task?
This skill answers that. It matches cognitive investment to task consequence — proportional depth, not maximum depth.
The Failure Mode You Must Recognize
Without orchestration, you either:
- Use zero skills (shallow — surface response ships unchallenged)
- Use all skills on every task (slow — over-investing on low-stakes work)
- Use the wrong skills (mismatched — deep temporal analysis on a CSS color choice)
The right depth is proportional. A CSS fix needs zero skills. A database schema needs five. This skill determines the right number.
The Protocol
Step 1 — CLASSIFY THE TASK
TASK PROFILE
────────────────────────────────────────
Task: [one sentence description]
Complexity: [low / moderate / high / extreme]
Consequence: [trivial / moderate / significant / critical]
Reversibility: [trivially / moderately / hard / permanent]
Novelty: [routine / somewhat novel / highly novel / unprecedented]
Breadth: [single-domain / cross-domain / full-stack]
────────────────────────────────────────
Artifact: The task profile. Step 2 uses this to assign depth.
Step 2 — ASSIGN DEPTH BUDGET
DEPTH BUDGET
────────────────────────────────────────
BUDGET A — Low stakes, reversible, routine:
Skills: 0. Standard answer. Move fast.
Skip remaining steps. Deliver.
BUDGET B — Moderate stakes, some novelty:
Skills: 1-2. Pick the most relevant.
Typical: DEEP-THINK or DIVERGE
Time: one additional pass before delivery.
BUDGET C — High stakes, hard to reverse:
Skills: 3-4. Thinking + challenging + checking.
Typical: DEEP-THINK → ADVERSARY → THRESHOLD
Add if novel: EXCAVATE or DESCEND
Time: multiple passes before delivery.
BUDGET D — Critical, permanent, unprecedented:
Skills: Full stack. Every relevant skill in sequence.
Typical: DEEP-THINK → DIVERGE → ADVERSARY → CONTRADICT →
PROVENANCE → FIDELITY → NEGATIVE-SPACE → THRESHOLD
Time: thorough multi-pass analysis.
This task: BUDGET [A/B/C/D]
Reasoning: [why this budget level — reference the task profile]
────────────────────────────────────────
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.
- 11d ago First seen · 200 lines · 26 tokens per session scan A f81fb7681edb
conductor is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,609 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
context-budget
Use when you need to check the current session's context usage and get recommendations for compaction or continuation.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
api-database-mongodb
Native MongoDB driver (the mongodb npm package) - MongoClient lifecycle, typed collections, CRUD result shapes, cursors, aggregation pipelines, index design, transactions.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.