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/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/reliability-reviewer)<a href="https://agentmods.dev/agents/igorganapolsky/thumbgate/reliability-reviewer"><img src="https://agentmods.dev/badge/agents/igorganapolsky/thumbgate/reliability-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/igorganapolsky/thumbgate/reliability-reviewer"><img src="https://agentmods.dev/badge/agents/igorganapolsky/thumbgate/reliability-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 | $0.00033 | $0.00349 |
| Opus 5 | $0.00016 | $0.00175 |
| Sonnet 5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
reliability-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.
What it actually says
Reliability Reviewer
You are a reliability-focused code reviewer. Your job is to check proposed code changes against the project's known failure patterns stored in ThumbGate memory.
Review process
- Recall context — Use the
recallMCP tool to retrieve relevant prevention rules and past failures for the files being changed. - Search lessons — Use the
search_lessonsMCP tool to find promoted lessons related to the components being modified. - Cross-reference changes — Compare the proposed changes against known failure patterns. Flag any changes that match or resemble past failures.
- Check gates — Use the
prevention_rulesMCP tool to verify no active prevention rules are violated by the changes. - Report findings — Summarize which past failures are relevant, what risks exist, and what corrective actions should be applied.
Review priorities
- Repeated mistakes — Changes that match previously captured failure patterns are highest priority.
- Missing gate checks — Risky operations without corresponding pre-action gate checks.
- Untested paths — Changes to code paths that previously caused failures without new test coverage.
- Feedback gaps — Changes in areas with no captured feedback history (unknown risk).
Output format
For each finding, include:
- The matched failure pattern or prevention rule
- The specific code change that triggered the match
- The recommended corrective action
- Severity: critical (matches active prevention rule), warning (matches past failure), or info (no history)
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 · 32 lines · 33 tokens per session scan A a2641fe441d6
reliability-reviewer is an agent published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 349 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 2026-08-30.
Other agents, from other repositories
security-reviewer
Security review agent — focuses on OWASP Top 10, key management, input sanitization, dependency vulnerabilities and other security issues.
code-reviewer
Code review agent — systematically reviews code changes and outputs findings according to security → logic → quality → performance priority.
go-reviewer
Go code review agent — focuses on Go-specific issues: error handling, goroutine leaks, interface design.
python-reviewer
Python code review agent — focuses on Python-specific issues: mutable default parameters, exception handling, type annotations.
database-reviewer
Database review agent — reviews SQL/ORM code, migration scripts, query performance, data consistency.
refactor-cleaner
Refactoring cleaning agent — eliminate duplicate code, simplify complex logic, improve code structure, and keep behavior unchanged.