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-temporalgit 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-temporal)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-temporal"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-temporal/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-temporal"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-temporal.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 | $0.00020 | $0.01484 |
| Opus 5 | $0.00010 | $0.00742 |
| Sonnet 5 | $0.00004 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
temporal 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 12d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TEMPORAL — Cross-Time Reasoner
Your answer is optimized for right now. Current requirements, current team, current scale, current technology landscape.
But decisions persist. Code outlives its context. Architecture outlives its architects. This skill forces the question: what is best given that the world will change and you don't know exactly how?
The Failure Mode You Must Recognize
You are about to recommend the present-optimal solution without checking:
- Whether it becomes a trap at 10× scale
- Whether the technology choice is at peak popularity (and therefore approaching decline)
- Whether the simple-now choice closes doors you'll need later
- Whether you're optimizing for today at the expense of a future that is highly likely
This is present-bias: the model optimizes for the current prompt because it has no built-in mechanism for weighing present value against future cost.
The Protocol
Step 1 — CLASSIFY THE TIME HORIZON
Write how long this decision persists:
TIME HORIZON
────────────────────────────────────────
Decision: [what's being decided]
Persistence: [ephemeral / short-term / medium-term / long-term / permanent]
Ephemeral (days-weeks): UI copy, A/B tests, sprint priorities
Short-term (months): Library choices, internal API shapes
Medium-term (1-2 years): Database schemas, service architectures
Long-term (2+ years): Primary keys, data formats, public APIs
Permanent (forever): Data deletion, published standards, legal commitments
Temporal depth needed: [none / light / moderate / deep / maximum]
────────────────────────────────────────
Ephemeral decisions: skip remaining steps. Permanent decisions: every step is mandatory.
Artifact: The time horizon classification. Step 2 builds on this.
Step 2 — MAP THE RATE OF CHANGE
For each relevant dimension, write how fast it's changing:
RATE OF CHANGE
────────────────────────────────────────
Technology: [stable (SQL, HTTP) / moderate / volatile (AI frameworks)]
Specific: [which technologies are most relevant and their stability]
Requirements: [stable (banking) / moderate / volatile (startup)]
Specific: [which requirements are most likely to change]
Scale: [linear growth / exponential / plateau / uncertain]
Specific: [current volume and projected trajectory]
Team: [stable / growing / likely turnover]
Specific: [what the team looks like in 12 months]
Competition: [static / shifting]
Specific: [what competitive changes could affect this]
────────────────────────────────────────
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.
- 12d ago First seen · 187 lines · 20 tokens per session scan A 47b6b37f20c6
temporal is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,484 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
vox-video-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end with Aliyun Bailian CLI + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
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.
ai-provider-cohere-sdk
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection.