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-domain-foldgit 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-domain-fold)<a href="https://agentmods.dev/skills/alperhankendi/ctxo/ctxo-domain-fold"><img src="https://agentmods.dev/badge/skills/alperhankendi/ctxo/ctxo-domain-fold/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-domain-fold"><img src="https://agentmods.dev/badge/skills/alperhankendi/ctxo/ctxo-domain-fold.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 | $0.00049 | $0.00633 |
| Opus 5.5 | $0.00020 | $0.00253 |
| Sonnet 5.5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
ctxo-domain-fold 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 yesterday.
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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fold domain knowledge with ctxo
When adopting or tuning the domain config
- Run
ctxo domain discoverfirst (a dry run: it writes nothing). It reads the commit subjects, branches, index and tracked files and proposesdomain.rules.trackerPrefixes,domain.tests.ruleTraitKeys,index.testsand the characterization and contract test markers (folders, file-name globs, Trait or Category values and custom test attributes). External IDs such as CWE or ISO keys, GitHub#Nissues and lowercase branch identifiers are evidence only: they need no config. - Review the evidence, then either edit
.ctxo/config.yamlby hand or runctxo domain discover --write, which adds the proposed values and removes none.--jsonprints the same evidence and proposal for a script. - A wrong value, once written, stays until you remove it by hand, and discovery (and
ctxo doctor) proposes it again until the evidence changes. Review before--write. - Do not reverse-engineer the config keys from ctxo's installed files: the discovery report names each key it proposes.
Before changing a context's code
- Find the context that owns the files: the generated path rule for the folder, or
docs/domain/contexts.yaml(each context lists itspathsand itscard). - Read the context's card before you edit: its rules, contracts and decisions are the behaviour the code must keep.
- With the ctxo MCP tools, call
get_domain_contextwith the symbol you will change (symbolId, or apath): it returns the context's card, its rules with their linked tests and code, terms, contracts and decisions. Then callget_rulefor each rule it lists that your change may affect, to see the tests that pin the rule and the decisions behind it. - To find business logic no rule pins yet, call
find_shadow_specsfor the context.
When behaviour changes
- Update the card in the same branch as the code: a changed rule, contract or decision goes into the card, not only into the commit message.
- Rule IDs are permanent. Never reuse or renumber one; retire a rule by marking it, and give a new rule a new ID.
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.
- yesterday Changed · +8 lines · +15 tokens per session 521726669649
- 2d ago First seen · 26 lines · 34 tokens per session scan A 6e84d2f39449
ctxo-domain-fold is a skill published in the GitHub repository alperhankendi/Ctxo (73 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 633 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 2026-10-24.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
skill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.