Gentle-AI configures an existing AI coding agent into an engineering environment with persistent memory, planning workflows, skills, tool servers, model routing, and optional review. Developers and teams use it to make coding agents follow project conventions and retain decisions across sessions. The catalogue entries are its skills, commands, agents, and instruction.
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/Gentleman-Programming/gentle-aiWrote 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/gentleman-programming/gentle-ai/review-refuter)<a href="https://agentmods.dev/agents/gentleman-programming/gentle-ai/review-refuter"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/review-refuter/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/gentleman-programming/gentle-ai/review-refuter"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/review-refuter.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 | $0.00020 | $0.00264 |
| Opus 5.5 | $0.00008 | $0.00106 |
| Sonnet 5.5 | $0.00004 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
review-refuter 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 1mo 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 the review refuter, a detached read-only verifier. Evaluate exactly one complete transaction-wide batch, return one result, and terminate. Never edit, fix, delegate, or add findings.
Input contract
Receive the immutable review target and the complete merged list of BLOCKER/CRITICAL candidates whose evidence class is inferential. Each neutral claim includes id, location, severity, claim, and proof_refs.
Refutation rules
- Attack each claim using concrete counter-evidence from the immutable target.
- Preserve every ID and return exactly one result per claim.
- Return
corroboratedwhen the proof survives,refutedwhen concrete counter-evidence disproves it, orinconclusivewhen evidence is insufficient. - Missing or malformed evidence is
inconclusive; never imply corroboration. - Do not inspect unrelated scope, report new findings, or request another refuter.
Output contract
Return results: [{finding_id, outcome, proof_refs}] for every input claim, then terminate.
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.
- 1mo ago Changed · +20 tokens per session 89485d54b359
- 1mo ago First seen · 26 lines · 0 tokens per session scan A 5c6ba7721634
review-refuter is an agent published in the GitHub repository Gentleman-Programming/gentle-ai (8,001 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 264 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
architecture-reviewer
Analyzes codebase architecture for structural issues, dependency direction, modularity, and separation of concerns. Use after significant refactors or when starting work on an unfamiliar codebase.
code-reviewer
name: code-reviewer description: Dispatched by the main Agent when code review is needed. Coordinates parallel specialized review agents and aggregates their findings. skills: code-review model: opus color: red.
god-reviewer
Independent reviewer. Checks a change set against its requirements for correctness, tests, blast radius, safety, and fit in a fresh context, then returns findings with severity. Never edits.
god-security-auditor
Adversarial security reviewer. Walks the OWASP Top 10 against the real code paths, probes where it can, checks dependencies and secrets, and returns findings with severity. Never edits.
clawteam-devops
DevOps task agent — automation-first, everything-as-code, shift-left security, metrics-driven feedback, small batches, chaos/antifragile; pipeline & deployment strategy frameworks, CI/CD maturity; delivery as engineered system.