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-meta-learninggit 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-meta-learning)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-meta-learning"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-meta-learning/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-meta-learning"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-meta-learning.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 | $0.00043 | $0.04154 |
| Opus 5.5 | $0.00017 | $0.01662 |
| Sonnet 5.5 | $0.00009 | $0.00831 |
| Haiku 4.5 | $0.00004 | $0.00415 |
Grade A, and why
meta-learning 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 14d 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 — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
META-LEARNING — Cognitive Evolution Engine (Premium)
Mathematical Compliance: This skill implements the DEPTH-MATHEMATICS specification. It computes and outputs ADS phase activation, CEI components, SI components, cognitive traces, and verifies Gates V5, V6. It provides the compounding intelligence mechanism — the system improves itself over time.
Research Basis:
- Wang et al. (2023) "Voyager: An Open-Ended Embodied Agent with Large Language Models" (arXiv:2305.16291) — automatic curriculum, ever-growing skill library, iterative prompting with self-verification
- Shinn et al. (2023) "Reflexion: Language Agents with Verbal Reinforcement Learning" (arXiv:2303.11366) — linguistic feedback, episodic memory, self-improvement without weight updates
- Gou et al. (2023) "CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing" (arXiv:2305.11738) — tool-interactive validation and progressive amendment
Your skill library is static. It doesn't learn. Every task starts from zero. The patterns you discovered in Task 1 are lost when Task 2 arrives. The CONDUCTOR's selection policy is hand-crafted, not learned.
This skill changes that. It extracts patterns from task outcomes, synthesizes new skills, updates the CONDUCTOR's policy, and validates everything against a regression suite. The system gets smarter over time — compounding intelligence.
The Failure Mode You Must Recognize
You are about to finish a task and move on. The orchestration log sits there. The patterns you discovered — which skills worked, which interferences mattered, which gates failed — are not captured. The next task starts with the same hand-crafted policy.
This is cognitive amnesia. The system has no memory of its own reasoning evolution.
New failure mode in v1.0: Pattern loss — reusable reasoning patterns discarded after each task. Policy staleness — CONDUCTOR policy doesn't adapt to model updates or domain shifts. Library rot — skills degrade without regression testing. Synthesis gap — no mechanism to create new skills from discovered patterns.
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.
- 14d ago First seen · 504 lines · 43 tokens per session scan A de73d3153b70
meta-learning is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 4,154 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 2026-10-03.
Other skills, from other repositories
agent-memory-testing
Use this skill when you need evidence-bounded memory write/read/update/delete, retention, contamination, isolation, provenance, and forgetting behavior; triggers include Agent 记忆 and Agent memory.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…