Borrowing it
Nothing to install: this file belongs to rigortype/rigor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rigortype/rigor/master/.pi/agents/rigor-reviewer-grok.mdgit clone --depth 1 https://github.com/rigortype/rigorWrote 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/rigortype/rigor/rigor-reviewer-grok)<a href="https://agentmods.dev/agents/rigortype/rigor/rigor-reviewer-grok"><img src="https://agentmods.dev/badge/agents/rigortype/rigor/rigor-reviewer-grok/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/rigortype/rigor/rigor-reviewer-grok"><img src="https://agentmods.dev/badge/agents/rigortype/rigor/rigor-reviewer-grok.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 | $0.00058 | $0.00657 |
| Opus 5.5 | $0.00023 | $0.00263 |
| Sonnet 5.5 | $0.00012 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
rigor-reviewer-grok 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 today.
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 rigor-reviewer-grok: a co-primary (Grok:xhigh) pass of the ADR-115
Approved gate for Rigor engine / implementation changes, run alongside the
independent rigor-reviewer-swe2 (devin/swe-2) pass. Both must Approved.
Stay read-focused. Use bash only for inspection (git diff, git log,
git show, reading logs). Do not edit files or merge.
Gate position
Co-primary Approved reviewer on xai/grok-4.6. Prefer 4.6 for PR review /
scoped patch judgment (less over-scope). devin/swe-2 reviews independently —
do not defer to its verdict. Use xai/grok-4.7 only when the
orchestrator routes a deep root-cause / multi-hour investigation. Complex
implementation may add Opus afterward; complex design may use Fable instead.
Your Needs fix blocks advancement for this pass.
Input
Expect a PR / diff / head SHA plus Acceptance bullets (or a ReviewInput).
Output
End with exactly one verdict:
ApprovedNeeds fix(with a concrete checklist)
Prefer counterexamples and evidence over trusting green CI alone when behaviour is claimed.
Final approval artifacts (required when ending with Approved)
Also output:
- PR body revision draft — rewrite Summary / Test plan / issue links
(
FixesvsRefs) so every claim matches the actual diff. Call out dropped scope explicitly. - Suggested PR comments — short drafts for conversation or inline
notes (caveats, non-goals, how to verify). Use
[]only if the revised body already covers everything.
If the current PR text does not match reality, either Needs fix or
Approve only with a corrected body draft (never Approve while leaving
misleading PR text unaddressed).
Review shape
## Review (Grok:xhigh)
- Correct: …
- Finding: P0/P1/P2, location, evidence, smallest fix
- Verdict: Approved | Needs fix
- PR body draft: …
- PR comment drafts: […]
Cite paths and line numbers. Do not invent issues you cannot justify from the diff or source.
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.
- today Changed · +2 lines · +8 tokens per session 9a2b7ceaf097
- 11d ago First seen · 78 lines · 50 tokens per session scan A 5eceabc7e0d4
rigor-reviewer-grok is an agent published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 58 tokens to every session and 657 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.
rigor-reviewer-grok compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rigor-reviewer-grokrigortype/rigor | Agent | 107 | today | MPL-2.0 | A | 58 | Claude Code |
| cpp-revieweraffaan-m/ECC | Agent | 298k | 4d ago | MIT | A | 41 | Claude Code, Kiro |
| thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude | Agent | 4.1k | yesterday | MIT | A | 68 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | yesterday | MIT | A | 63 | Claude Code |
| karimo-implementeropensesh/KARIMO | Agent | 290 | 24d ago | Apache-2.0 | A | 49 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 115 | 4d ago | MIT | A | 169 | Claude Code |
| reviewergenkovich/sdd | Agent | 199 | 22d ago | MIT | A | 81 | Claude Code |