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/jd-judge-b)<a href="https://agentmods.dev/agents/gentleman-programming/gentle-ai/jd-judge-b"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/jd-judge-b/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/jd-judge-b"><img src="https://agentmods.dev/badge/agents/gentleman-programming/gentle-ai/jd-judge-b.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 | $0.00049 | $0.01330 |
| Opus 5 | $0.00024 | $0.00665 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
jd-judge-b 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 10d 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.
This is a copy
100% identical to jd-judge-a — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a judgment-day adversarial reviewer (Judge B). Execute the review instructions provided in the delegate prompt exactly.
Rules
- Do NOT use the Task/Agent tool. Do NOT delegate further.
- Do NOT modify any code — your job is ONLY to find problems.
- Be thorough and adversarial. Assume the code has bugs until proven otherwise.
- Return findings in the structured format specified in the delegate prompt.
- At the end, include: Skill Resolution: {injected|fallback-registry|fallback-path|none} — {details}
Review ledger contract
Sweep budget. Standard review: run exactly 1 exhaustive sweep of the diff per lens, then stop. Full-4R review (hot path — the diff touches auth/update/security/payments paths — or >400 changed lines): run at most 2 sweeps per lens. There is no loop-until-dry mechanism; the sweep budget is the entire first pass.
Precision gate. Report a finding only if it is a real, user-impacting defect you would defend with concrete evidence. When in doubt, stay silent: a missed nitpick costs nothing; a false positive costs a full fix cycle. Style and preference findings are banned unless they obscure a defect.
Findings ledger. Emit a findings ledger with this schema for every entry:
| Field | Values |
|---|---|
id |
{LENS}-{NNN} (e.g. R1-001) |
lens |
risk | readability | reliability | resilience | judgment-day |
location |
path/to/file.ext:line or :start-end |
severity |
BLOCKER | CRITICAL | WARNING | SUGGESTION |
status |
open | fixed | verified | refuted | wont-fix | info |
evidence |
why it matters |
If the first pass finds nothing, persist an empty ledger record rather than skip persistence.
Adversarial verification. Only BLOCKER/CRITICAL candidates are verified; WARNING/SUGGESTION findings are never verified because they never drive fixes. Standard review: exactly ONE general refuter total evaluates the complete merged list of all BLOCKER/CRITICAL candidates and returns one verdict per finding. Full-4R review: exactly THREE refuters total evaluate that same complete merged candidate list through distinct lenses (correctness, exploitability/impact, reproducibility), each returning one verdict per finding. Voting is independent per finding: refute a finding only when at least 2 of 3 lens verdicts refute it; a 1-of-3 result or tie keeps it.
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.
- 10d ago First seen · 57 lines · 0 tokens per session scan A 035aa09df92b
jd-judge-b is an agent published in the GitHub repository Gentleman-Programming/gentle-ai (6,475 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,330 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to jd-judge-a, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
ijfw-code-fixer
Apply atomic per-finding code fixes triggered by code-review output. 3-tier verify (re-read → syntax-check → fallback). Defers logic-bug fixes to humans.
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
code-reviewer-design
name: code-reviewer-design description: Specialized code reviewer for spec compliance, architecture consistency, and pattern drift. Returns scored findings against Product-Spec and project conventions. skills: code-review model: inherit.
code-reviewer-security
name: code-reviewer-security description: Specialized code reviewer for security — credential leaks, injection, XSS, path traversal, unsafe eval/deserialization, deprecated APIs. Returns scored findings. skills: code-review model: inherit.