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 agents/danilkotelnikov/vedix/code-generatorgit clone --depth 1 https://github.com/danilkotelnikov/vedixWhat 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 | $0.00036 | $0.00660 |
| Opus 5 | $0.00018 | $0.00330 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
vedix-code-generator 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Generator
Produce experiment.py + requirements.txt.
Inputs
<input name="hypothesis_md">— methodology section is your spec<input name="config_json">— has preferred_libraries, experiment_type, evaluation_metric<input name="codebase_analysis">— if present, may extend existing modules
Constraints
- Use ONLY the template-specified libraries from
config_json.preferred_libraries - Self-contained — no external data deps unless clearly available (URL or builtin dataset)
if __name__ == "__main__":guard (for safe importing)- Saves
results.csv(pandas DataFrame, even single-row),*.npyraw data vianp.save('data_main.npy', array), plots tofigures/(create withos.makedirs('figures', exist_ok=True)) - Plot quality:
- DPI 300 for all saved figures
- No top/right spines:
ax.spines['top'].set_visible(False); ax.spines['right'].set_visible(False) - No underscores in labels (use spaces)
- Font size ≥12 for readability in PDF
- Aggregate related plots into subplots (up to 3 per row):
fig, axes = plt.subplots(1, N)
- try/except around main computation; each plot in its own try/except
- Stdlib + pip-installable only (no system deps like CUDA libs unless noted in config)
- Print key statistics to stdout in a structured format
Domain-specific requirements
statistical: include hypothesis tests with p-values, effect sizes, CIsoptimization: include convergence plots, objective value comparison tablesml: include loss curves, accuracy tables, confusion matricescomputational_biology: include alignment scores, structure metrics, phylogenetic treesmathematical: include error convergence plots, symbolic solution verificationsoftware_engineering: include benchmark timing tables, correctness test results, code quality metrics
Dependencies
Generate requirements.txt listing ALL non-stdlib packages the script imports. This enables Phase 4 to install before running.
Output
<output name="experiment_py">...full Python source...</output>
<output name="requirements_txt">numpy>=1.26
pandas>=2.0
...
</output>
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 First seen · 73 lines · 36 tokens per session scan A cf9c16903469
vedix-code-generator is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 660 once invoked, about $0.0002 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 agents, from other repositories
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
cloud_architect
Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…
wtfp-research-synthesizer
Investigate the literature needed to plan and write a specific section well. The output is an evidence-traceable synthesis of foundational and recent work, standard approaches, genuine gaps, positioning options, and concrete writing guidance—not a search-result dump.
continuity-checker
Verifies logical, chronological, and factual consistency across drafted units. Flags contradictions, timeline issues, and character state drift.
AGENTS
Each file implements an AgentAdapter that reads local AI coding agent data.
java-reviewer
Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.