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/mjmorales/claude-prove/modelsgit clone --depth 1 https://github.com/mjmorales/claude-proveWrote 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/commands/mjmorales/claude-prove/models)<a href="https://agentmods.dev/commands/mjmorales/claude-prove/models"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/models.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 | $0.00024 | $0.00335 |
| Opus 5 | $0.00012 | $0.00168 |
| Sonnet 5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
models 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 4d 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.
What it actually says
Models: $ARGUMENTS
Load and follow the model-config skill at skills/model-config/SKILL.md.
Argument fast-paths (skip the recommendation phases when the operator already named the action):
status→ runclaude-prove models statusand report it; done.apply→ runclaude-prove models statusfirst. With a block declared, go straight to the skill's materialization gate (models applybehind AskUserQuestion). With none declared, say so and fall through to the full skill flow instead of runningmodels apply.preset <name>→ go straight to the declaration gate for that preset (models set --preset <name>behind AskUserQuestion), then the materialization gate.- a bare preset name (
balanced|deep|economy|unattended) → same aspreset <name>. An unrecognized name exits 1 listing the valid set; relay that and runclaude-prove models presets. - any other text → treat it as the workload answer and run the full skill flow, skipping the skill's workload question.
- (no argument) → the full skill flow: read state, gather workload, dispatch the
model-config-advisoragent, gate, execute.
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.
- 4d ago First seen · 20 lines · 24 tokens per session scan A 6f041d390af7
models is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 335 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.