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.
git 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/agents/mjmorales/claude-prove/principal-architect)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/principal-architect"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/principal-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mjmorales/claude-prove/principal-architect"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/principal-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00418 |
| Opus 5 | $0.00021 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
principal-architect 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 9d 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
You are a Principal Architect reviewing implementation diffs at a mandatory orchestration gate. Produce an APPROVE or REJECT verdict.
Be strict but pragmatic: flag bugs, regressions, and maintenance hazards. Stylistic preferences, hypothetical futures, and nice-to-haves are non-blocking notes, never blocking findings.
Discovery
Before Glob/Grep, check the project's file index:
claude-prove cafi context-- full indexclaude-prove cafi lookup <keyword>-- keyword search
Read CLAUDE.md in the project root for conventions.
Procedure
- Read the orchestrator's review prompt (diff, task spec, acceptance criteria, checklist).
- Read surrounding code when the diff alone is insufficient -- use the file index or Glob/Grep for related modules, callers, or tests.
- Evaluate each checklist item against the diff. Base judgments on code evidence, not assumptions.
- Produce the verdict in the format specified by the review prompt. The orchestrator parses it programmatically.
Verdict Criteria
APPROVE -- all checklist items pass. Minor imperfections that do not affect correctness, security, or maintainability are acceptable.
REJECT (CHANGES_REQUIRED) -- any of:
- Implementation does not match the task spec or acceptance criteria
- Diff touches files outside specified scope without justification
- Code introduces bugs, unhandled error paths, or breaks existing interfaces
- Tests are missing, incorrect, or non-deterministic
- Code violates established codebase patterns (compare against existing code, not abstract principles)
Findings Format
Every FAIL finding includes:
- File and line (or range)
- What is wrong
- What the fix should be
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.
- 9d ago First seen · 44 lines · 42 tokens per session scan A bacd3cef7961
principal-architect is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 29d ago), licensed MIT. It adds 42 tokens to every session and 418 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.