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 commands/oxy-hq/skills/validategit clone --depth 1 https://github.com/oxy-hq/skillsWhat 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 | $0.00021 | $0.00544 |
| Opus 5 | $0.00010 | $0.00272 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
oxy:validate 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Oxy Configuration
Validate all Oxy configuration files in the current project to catch errors before running workflows or agents.
What to Validate
oxy validate checks these file types:
- Agent files - All
.agent.ymlfiles - Workflow files - All
.workflow.ymland.procedure.ymlfiles - App files - All
.app.ymlfiles
Note: oxy validate does NOT process semantic layer files (.view.yml, .topic.yml).
Use oxy build to validate and compile the semantic layer.
Note: config.yml is validated automatically when any oxy command loads the
configuration — you do not need to run a separate validate step for it.
Steps
-
Check for Oxy installation
- Run
oxy --versionto verify Oxy CLI is installed - If not found, inform the user they need to install Oxy first
- Run
-
Run validation
- Execute
oxy validatecommand - This validates config.yml, all agent files, and all workflow files
- Execute
-
Report results
- If validation passes: Report success with summary
- If validation fails:
- Show all errors with file paths and line numbers
- Explain what each error means in clear terms
- Suggest fixes where possible
Error Handling
Common validation errors and how to help:
- YAML syntax errors: Show the line with the error and suggest the fix
- Missing required fields: List which fields are missing and what values they should have
- Invalid references: Explain which referenced entity/view/dimension doesn't exist
- Type mismatches: Show expected vs actual types
Success Message
When validation passes, show a clear success message like:
✅ Oxy validation passed!
Validated:
- X agent files
- Y workflow files
- Z app files
Your Oxy project is ready to run.
Note: To validate the semantic layer, run `oxy build`.
Notes
- Always run from the project root directory (where config.yml is located)
- This command doesn't modify any files, it only checks them
- Run this before
/oxy:testto catch workflow/agent/app errors early - For semantic layer errors, use
/oxy:buildinstead
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.
- 2d ago First seen · 77 lines · 21 tokens per session scan A 8935f8c25793
oxy:validate is a command published in the GitHub repository oxy-hq/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 544 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.