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 topprismdata/cultivating-ml-agent --skill claudeceptiongit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote 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/topprismdata/cultivating-ml-agent/claudeception)<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/claudeception"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/claudeception/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/topprismdata/cultivating-ml-agent/claudeception"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/claudeception.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 | $0.00096 | $0.01899 |
| Opus 5.5 | $0.00038 | $0.00760 |
| Sonnet 5.5 | $0.00019 | $0.00380 |
| Haiku 4.5 | $0.00010 | $0.00190 |
Grade A, and why
claudeception 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 1mo 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudeception
Continuous learning system that extracts reusable knowledge from work sessions into Claude Code skills. Each extracted skill makes future sessions smarter.
When to Extract
Extract when you encounter:
- Non-obvious solutions — Required >10 min investigation, not in docs
- Error resolution — Misleading error messages, non-obvious root causes
- Workaround discovery — Tool/framework limitations requiring experimentation
- Configuration insights — Project-specific setups differing from standard
- Trial-and-error success — Multiple approaches before finding what worked
- Self-critique catches — A predicted risk actually materialized (high-value signal)
- Path efficiency insights — A systemic execution pattern worth improving
Dual-Track Classification
Before creating, classify the knowledge:
| Track | When | Template sections |
|---|---|---|
| Bug fix | Defect, failure, error resolution | Problem, Symptoms, Root Cause, Solution, Prevention |
| Knowledge | Best practice, pattern, workflow optimization | Context, Guidance, Why This Matters, When to Apply |
This determines the skill's section structure.
Extraction Process
Step 1: Overlap Detection (BEFORE creating)
Search existing skills for overlap across 5 dimensions:
| Dimension | What to compare |
|---|---|
| Problem statement | Same underlying issue? |
| Root cause | Same technical cause? |
| Solution approach | Same fix? |
| Referenced files | Same code paths? |
| Prevention rules | Same advice? |
Scoring: Count matching dimensions.
| Overlap | Action |
|---|---|
| High (4-5 match) | Update existing skill with fresher context |
| Moderate (2-3 match) | Create new, add See also: cross-reference |
| Low (0-1 match) | Create new normally |
Why: Two skills describing the same problem will drift apart. Update rather than duplicate.
Step 2: Research (When Appropriate)
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.
- 1mo ago First seen · 231 lines · 96 tokens per session scan A 65e17e2bfb7c
claudeception is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 11d ago), licensed MIT. It adds 96 tokens to every session and 1,899 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
python-output-buffering-background-scripts
Python buffers stdout and stderr when output is not connected to a terminal (TTY). This causes log files to appear empty even though the process is running and producing output. Use when: (1) Background script log file is empty but process is running (visible in ps), (2) Redirecting Python script output to a file and…
huggingface-hub
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.