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 alperhankendi/Ctxo --skill ctxo-understandgit clone --depth 1 https://github.com/alperhankendi/CtxoWrote 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/alperhankendi/ctxo/ctxo-understand)<a href="https://agentmods.dev/skills/alperhankendi/ctxo/ctxo-understand"><img src="https://agentmods.dev/badge/skills/alperhankendi/ctxo/ctxo-understand/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/alperhankendi/ctxo/ctxo-understand"><img src="https://agentmods.dev/badge/skills/alperhankendi/ctxo/ctxo-understand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00586 |
| Opus 5.5 | $0.00020 | $0.00234 |
| Sonnet 5.5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
ctxo-understand 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 16d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient with ctxo before diving in
At the start of a new task:
get_context_for_taskwith the matching taskType (fix | extend | refactor | understand).- For unfamiliar areas:
get_architectural_overlay(layer map) andget_symbol_importance(critical symbols). - Don't know the symbol name?
search_symbols(name/regex) orget_ranked_context(natural language) before grepping or browsing directories.
Then read the files ctxo points you to. Reading a file to see its contents needs no index call.
Which tool for which question
| Question | Tool |
|---|---|
| Reviewing a PR or recent changes | get_pr_impact (one call: changed symbols, blast radius, co-change) |
| What breaks if I change this symbol? | get_blast_radius, then get_why_context |
| Why does this code look like this? Any reverts? | get_why_context |
| What does this symbol do and depend on? | get_context_for_task(taskType: "understand") or get_logic_slice (L2 overview, L3 full closure) |
| Fixing a bug | get_context_for_task(taskType: "fix") |
| Adding or extending a feature | get_context_for_task(taskType: "extend") |
| Refactoring | get_context_for_task(taskType: "refactor") |
| Who uses this? Is it safe to delete or rename? | find_importers, then get_blast_radius |
| Class inheritance (extends, implements) | get_class_hierarchy |
| Unused symbols and files | find_dead_code |
| Complexity and churn hotspots | get_change_intelligence |
| Symbols in recently changed files | get_changed_symbols |
| Find a symbol by name or regex | search_symbols |
| Find code for a natural-language question | get_ranked_context |
| Layer map of the project | get_architectural_overlay |
| Candidate bounded contexts / context map | get_architectural_overlay(mode: "contexts"), then candidate: <id> |
| Most central symbols | get_symbol_importance |
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.
- 16d ago Changed · +1 lines bb59a2af680b
- 17d ago Changed · +23 lines · +9 tokens per session 425fbb0f72cd
- 2mo ago First seen · 15 lines · 41 tokens per session scan A 955f61aecdfb
ctxo-understand is a skill published in the GitHub repository alperhankendi/Ctxo (74 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 586 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 2026-08-30.
ctxo-understand compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ctxo-understandalperhankendi/Ctxo | Skill | 74 | 7d ago | MIT | A | 50 | Claude Code, Codex |
| gentle-ai-collab-perfectGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 106 | Claude Code, Codex |
| issue-creationGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 30 | Claude Code, Codex |
| skill-creatorGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 27 | Claude Code, Codex |
| work-unit-commitsGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 33 | Claude Code, Codex |
| cognitive-doc-designGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 33 | Claude Code, Codex |
| comment-writerGentleman-Programming/gentle-ai | Skill | 8.6k | yesterday | MIT | A | 29 | Claude Code, Codex |