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 agentmods add skills/dinglebear-ai/cortex/skill-improvement-assessmentnpx skills add dinglebear-ai/cortex --skill skill-improvement-assessmentgit clone --depth 1 https://github.com/dinglebear-ai/cortexWrote 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/dinglebear-ai/cortex/skill-improvement-assessment)<a href="https://agentmods.dev/skills/dinglebear-ai/cortex/skill-improvement-assessment"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/cortex/skill-improvement-assessment.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.01173 |
| Opus 5 | $0.00044 | $0.00587 |
| Sonnet 5 | $0.00018 | $0.00235 |
| Haiku 4.5 | $0.00009 | $0.00117 |
Grade B, and why
skill-improvement-assessment scanned grade B with 1 finding 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 5d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
at you (for example "ignore previous instructions", "you are now in Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 5d ago First seen · 112 lines · 88 tokens per session scan B 6811b0280cc0
skill-improvement-assessment is a skill published in the GitHub repository dinglebear-ai/cortex (3 stars, last pushed today), licensed AGPL-3.0. It adds 88 tokens to every session and 1,173 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
using-axon
Use Axon for RAG, web search, source indexing, extraction, memory, and grounded answers over indexed docs, repos, feeds, or web content.
website-design-clone
Use when the user wants an agent-ready DESIGN.md derived from a site's observable visual language using Axon brand, scrape, and screenshot evidence.
rag-synthesize
RAG synthesis prompt for axon ask — source-grounded, depth-adaptive, injection-hardened. Loaded at runtime by src/vector/ops/commands/ask/synthesisprompt.rs.
cli
Route web search, source indexing, extraction, RAG, jobs, and watch tasks through the local Axon CLI.
knowledge-base
Use when crawling docs, ingesting source families, building or refreshing a Qdrant-backed RAG corpus, capturing docs sections, or producing LLM-ready markdown.
research-papers
Use when the user wants a literature review, paper summary, research landscape, or sourced synthesis from papers, reports, abstracts, or converted PDFs.