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/report-issuegit 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/report-issue)<a href="https://agentmods.dev/commands/mjmorales/claude-prove/report-issue"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/report-issue.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 5.1 | $0.00014 | $0.00671 |
| Opus 5 | $0.00007 | $0.00336 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
report-issue 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 6d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Issue: $ARGUMENTS
File a GitHub issue against the prove plugin using gh CLI.
Step 0: Verify gh CLI
gh auth status 2>&1
If not installed: "Install the GitHub CLI: https://cli.github.com/ then run gh auth login"
If not authenticated: "Run gh auth login to authenticate"
Stop on auth failure.
Step 1: Determine issue type
If $ARGUMENTS is provided, infer type from context. Otherwise, AskUserQuestion (header: "Issue Type"):
- "Bug Report" — something is broken or behaving unexpectedly
- "Feature Request" — a new capability or improvement
- "Documentation" — missing, unclear, or incorrect docs
Step 2: Gather context
Read the plugin version:
cat "$PLUGIN_DIR/.claude-plugin/plugin.json" 2>/dev/null | grep version
Bug reports: plugin version, actual vs expected behavior, reproduction steps, error output, which command/skill. Ask user for anything not clear from $ARGUMENTS.
Feature requests: what the user wants, motivation/use case, implementation ideas.
Documentation: what is missing or wrong, where the user expected to find it.
Step 3: Draft the issue
Compose using the appropriate template. Present via AskUserQuestion (header: "Draft").
Bug Report:
## Bug Report
**Plugin version**: vX.Y.Z
**Command/Skill**: /prove:<name>
### What happened
<description>
### Expected behavior
<description>
### Steps to reproduce
1. ...
### Error output
```
<paste if available>
```
### Environment
- OS: <detected>
- Claude Code version: <if known>
Feature Request:
## Feature Request
**Plugin version**: vX.Y.Z
### What
<description>
### Why
<motivation / use case>
### Proposed approach
<ideas, if any>
Documentation:
## Documentation Issue
**Plugin version**: vX.Y.Z
### What's missing or wrong
<description>
### Where I looked
<file or command>
Options: "Submit" / "Edit" / "Cancel"
On "Edit": let user modify, then re-present. On "Cancel": stop.
Step 4: Determine labels
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.
- 6d ago First seen · 130 lines · 14 tokens per session scan A 5a24776f1ad8
report-issue is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 26d ago), licensed MIT. It adds 14 tokens to every session and 671 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
commit
智能生成 Git 提交信息并提交.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
release-plan
Command "release-plan" from alisunstar/OpenSunstar, covering /rd:release-plan — 发布计划, 先读, 执行, 产物 and 人工确认.