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/updategit 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/update)<a href="https://agentmods.dev/commands/mjmorales/claude-prove/update"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/update.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 | $0.00011 | $0.04013 |
| Opus 5 | $0.00005 | $0.02006 |
| Sonnet 5 | $0.00002 | $0.00803 |
| Haiku 4.5 | $0.00001 | $0.00401 |
Grade B, and why
update scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
claude-prove schema validate --file "$(pwd)/.claude/settings.json" How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Configuration
Validate .claude/.prove.json and .claude/settings.json against current schema, detect drift, and apply migrations with user approval. See UPDATES.md at the plugin root for the human-readable migration guide.
All schema tool calls use --file with an absolute path to the project's config. Run against the user's current working directory, not the plugin directory.
Step 0: Pre-flight
0a: Resolve plugin location
Dogfooding shortcut: if $(pwd)/.claude-plugin/plugin.json exists, set PLUGIN_DIR = $(pwd) and skip the CLI call below. Otherwise:
claude-prove install latest
Apply these rules to the JSON output, in order:
- Halt if
localis null. Message: "Plugin not installed — runclaude plugin install prove@prove." Do not proceed. - Set
PLUGIN_DIR = local.installPath. This path is referenced as$PLUGIN_DIRin later steps; substitute the literal value when issuing commands. - Record
local.versionfor the pinned reference in CLAUDE.md. - Warn on remote mismatch, then continue. If
remote.versiondiffers fromlocal.version, surface: "Newer release available:local.version→remote.version. Runclaude plugin update prove@proveto upgrade, then re-run/prove:update." Continue the rest of the skill against the locally installed version — this skill syncs configs against what is on disk, never against an unreleased remote. - Surface
errors.local/errors.remoteif present, but do not abort unless rule 1 triggered.
0b: Guard working directory
Verify $(pwd) is NOT inside ~/.claude/ — prevents accidentally mutating the plugin cache. If it is (and the dogfooding shortcut above did not fire), halt: "Run /prove:update from your project root, not inside the plugin cache."
0c: Bootstrap if .prove.json is missing
If $(pwd)/.claude/.prove.json does not exist, AskUserQuestion (header: "Bootstrap"):
- "Create minimal config" — write
{"schema_version": "0"}to.claude/.prove.jsonand continue to Step 1 - "Run /prove:init instead" — suggest the full init flow and stop
- "Cancel" — stop
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 · 180 lines · 11 tokens per session scan B a4465f16520c
update is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 4,013 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.