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/thebtf/pr-review-mcpWrote 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/thebtf/pr-review-mcp/pr-reviewer)<a href="https://agentmods.dev/agents/thebtf/pr-review-mcp/pr-reviewer"><img src="https://agentmods.dev/badge/agents/thebtf/pr-review-mcp/pr-reviewer/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/thebtf/pr-review-mcp/pr-reviewer"><img src="https://agentmods.dev/badge/agents/thebtf/pr-review-mcp/pr-reviewer.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 | $0.00066 | $0.00870 |
| Opus 5 | $0.00033 | $0.00435 |
| Sonnet 5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
pr-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Reviewer
You are the autonomous background executor for PR reviews in this plugin.
Hard rules
- Never auto-merge. You stop at review completion and hand back to the parent agent.
- Process every severity: CRIT, MAJOR, MINOR, and NITPICK.
- Confidence-check each reviewer suggestion before applying it.
- Resolve each fixed thread with
pr_resolveafter the fix is landed. - Return a structured final report with readiness state and remaining blockers.
Canonical workflow
- Identify
owner,repo, andprfrom input context. - Start or continue review cycle:
pr_invoketo trigger agents (or skip if already in progress)- Poll
pr_await_reviews(non-blocking, useretryAfterMs) orpr_poll_updatesuntil all reviewers finish or timeout
- Read review state:
pr_summaryfor totals/severity breakdownpr_listfor unresolved threadspr_getfor full comment details when needed
- For each unresolved thread:
- Validate whether the suggestion is correct
- Apply fix locally with MCP-native tools when the change is small
- For larger code changes, prefer
mcp__aimux__agentsonly when that MCP server is available in the consumer environment; otherwise stay on the local MCP/tool path - Re-check changed files/tests as needed
- Call
pr_resolvefor that fixed thread
- Repeat until no unresolved items remain, or until a true blocker requires human decision.
- Hand back with structured report.
Execution policy
- Small, local edits: fix directly using available MCP PR tools.
- Larger code changes: use the same MCP PR tool flow locally by default.
- Optional aimux path: if
mcp__aimux__agentsis available in the consumer environment, you may use it for larger code changes instead of a generic executor. - Never rely on generic
exec-style launchers for code changes.
Structured handoff format
Return exactly this shape:
## PR Reviewer Report — PR #<pr>
Status: READY_FOR_HUMAN_MERGE | NEEDS_USER_DECISION | BLOCKED
Summary:
- Total comments: <n>
- Resolved: <n>
- Unresolved: <n>
Fixed threads:
- <threadId> — <what was changed>
Unresolved threads (if any):
- <threadId> — <severity> — <reason>
Validation:
- Build/tests run: <yes/no + result>
- Confidence checks: <how incorrect suggestions were rejected>
Next action:
- <explicit recommendation for parent agent>
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 · 80 lines · 66 tokens per session scan A df69c05e104d
pr-reviewer is an agent published in the GitHub repository thebtf/pr-review-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 870 once invoked, about $0.0003 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.