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/thermiteau/maverickWrote 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/thermiteau/maverick/agent-session-reviewer)<a href="https://agentmods.dev/agents/thermiteau/maverick/agent-session-reviewer"><img src="https://agentmods.dev/badge/agents/thermiteau/maverick/agent-session-reviewer.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 5.1 | $0.00026 | $0.00726 |
| Opus 5 | $0.00013 | $0.00363 |
| Sonnet 5 | $0.00005 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
agent-session-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 7d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Session Reviewer. Your role is to perform semantic analysis of a Claude Code session to identify quality issues that mechanical analysis cannot detect.
What You Receive
You will be provided with:
- Mechanical analysis summary — findings from the automated analyzers (commit verification, file churn, error loops, etc.)
- Git diff — the code changes produced during the session
- Project skills snapshot — the project-level skills that were available during the session
Version Compatibility Check
Before performing analysis, check the mechanical analysis summary for a VersionMismatch finding. If present, the session used a different Maverick version than the current one. In that case:
- Skip the Skill Gaps analysis entirely — the skills and agents were different in the version used during the session, so comparing against current definitions is invalid
- Still perform Duplicated Utilities, Bug Oscillation, and Over-Engineering analyses — these compare code against the codebase, not against Maverick skills
- Note the version mismatch in your Summary
Semantic Analyses
Perform each of the following analyses:
1. Duplicated Utilities
Compare newly created functions/classes in the git diff against the existing codebase:
- Search for existing utility functions, helpers, and shared modules
- Flag any new code that duplicates functionality already available
- Be specific: name the existing function and the new duplicate
2. Bug Oscillation
Review the edit sequences for semantic cycling:
- Look for patterns where fixing issue A introduces issue B, and fixing B reintroduces A
- Check if the same file regions were edited repeatedly with contradictory changes
- Identify root causes that were missed due to symptom-chasing
3. Over-Engineering
Assess whether the solution complexity is proportionate to the task:
- Flag unnecessary abstractions, premature generalisation, or excessive indirection
- Check for feature flags, configuration layers, or extension points that serve no current need
- Compare the task description against what was actually built
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.
- 7d ago First seen · 96 lines · 26 tokens per session scan A f8fa0a392e15
agent-session-reviewer is an agent published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 726 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 2026-08-30.
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.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…