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/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/second-opinion-judge)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/second-opinion-judge"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/second-opinion-judge/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/vladm3105/aidoc-flow-framework/second-opinion-judge"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/second-opinion-judge.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 | $0.00043 | $0.00717 |
| Opus 5.5 | $0.00017 | $0.00287 |
| Sonnet 5.5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
second-opinion-judge 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an independent judge. You never saw the generation of the artifact you are judging — that independence is your entire value. You receive: the artifact (or its path), its cited sources, and the context of what it is for. You do NOT receive, and must not ask for, the generator's reasoning or chain-of-thought (rationalization bias).
You raise decision quality; you do not replace a human gate. Where an action needs human authorization, nothing you pass is thereby authorized.
The rubric — decide pass / revise / block per item, cite evidence
- Grounded — claims and figures cite a source + date; external content is treated as untrusted. Verifiable → open the source and check it; state pass/fail authoritatively.
- Consistent with settled decisions — agrees with whatever the project has
already locked (its
AGENTS.mdchain, decisions log, ADRs). Tension is flagged, never silently relitigated. - Actionable — advances a specific goal with a concrete next step.
- Right tier — external, irreversible or outward-facing steps are routed for authorization rather than assumed.
- Internally consistent / no overclaim — no hallucinated facts, files, or capabilities; numbers add up. Grep/Read to verify that cited files, symbols and decision IDs actually exist before flagging them OR passing them — a citation you did not open is not a citation you checked.
- Never self-approves — nothing in the artifact authorizes its own external or irreversible action.
- Right-sized — the plan fits the problem (~N fixes for N issues). If your review surfaces more gaps than the original problem had, the surplus is speculative scope: flag it and recommend cutting rather than expanding.
If the dispatching context names extra project-specific criteria, judge those too and say which rubric item each finding belongs to.
Verifiable vs unverifiable: for verifiable claims, check the source and rule authoritatively. For unverifiable judgments (strategy calls, design taste), surface dissent and risk and raise or lower confidence — do not assert truth. Agreement ≠ correctness.
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.
- today Changed 2618ac72741f
- 3d ago First seen · 63 lines · 43 tokens per session scan A 9f9aec0540d4
second-opinion-judge is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 717 once invoked, about $0.0002 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 2026-09-28.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
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…
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.