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/initgit 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/init)<a href="https://agentmods.dev/commands/mjmorales/claude-prove/init"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/init.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 | $0.00027 | $0.03518 |
| Opus 5 | $0.00014 | $0.01759 |
| Sonnet 5 | $0.00005 | $0.00704 |
| Haiku 4.5 | $0.00003 | $0.00352 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize a prove project
Two halves run here:
- Stack config — delegate detection and validator emission to
claude-prove install init-config, then layer interactive UX for scope, validator review,.gitignore, references, and CLAUDE.md. - Project-identity bootstrap — drive a conversational interview (or honor selection flags) and author
charter.md,team.md, and a contributor record, then bring the identity chain live: register the contributor in the scrum registry (minting its CT-UUID) and offer operator-of-record + default-contributor wiring. The CLI runs the mechanical pre-flight checks and scaffolds skip-if-exists skeletons; you author the prose content into them.
claude-prove install init-config is the source of truth for validator detection. It writes <cwd>/.claude/.prove.json, preserves user-custom validators, and carries every other top-level key (scopes, reporters, claude_md, tools, ...) across re-runs.
Invocation modes
Read the slash-command arguments to pick the identity-bootstrap scope. Flags map to the artifact set:
--with-charter→ charter only (combinable with--with-team)--with-team→ team only (combinable with--with-charter)--full→ charter + team + contributor--form→ full set, but batch every interview question into one form (collect all answers up front), then author all artifacts in one pass- (no flag) → ask the operator which artifacts to bootstrap, then proceed
Division of labor: the CLI does the mechanical work — pre-flight checks and skip-if-exists scaffolding; you do the interview and write the prose. Author only into skeletons the CLI just created; never overwrite a skipped (already-existing) artifact, and never re-run or reimplement the pre-flight/scaffolding yourself — call the CLI for it.
Step 0: Guard
- Verify
$PLUGIN_DIRis set. If not, error: "Cannot resolve plugin directory." - Verify
$(pwd)is NOT inside~/.claude/. If it is, error: "You are inside the plugin directory. Run this command from your project root."
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 · 300 lines · 27 tokens per session scan A 04c199ef9461
init is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 3,518 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.