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.
npx skills add easyinplay/harnessed --skill second-opiniongit clone --depth 1 https://github.com/easyinplay/harnessedWrote 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/skills/easyinplay/harnessed/second-opinion)<a href="https://agentmods.dev/skills/easyinplay/harnessed/second-opinion"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/second-opinion/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/skills/easyinplay/harnessed/second-opinion"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/second-opinion.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 | $0.00100 | $0.01539 |
| Opus 5.5 | $0.00040 | $0.00616 |
| Sonnet 5.5 | $0.00020 | $0.00308 |
| Haiku 4.5 | $0.00010 | $0.00154 |
Grade A, and why
verify-second-opinion 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-second-opinion workflow (v3)
Overview
1-phase sub-workflow — 编排契约改动时的跨模型第二意见 (Phase 54 T2)。
| phase | id | upstream | model | capability | gate |
|---|---|---|---|---|---|
| 1 | 01-second-opinion |
gstack | sonnet | {{ capabilities.codex.cmd }} |
judgments.stage-routing.verify-second-opinion-orchestration.fires |
判据不是交给模型的判断题。harnessed facts 把 git diff --name-only <last release tag>
与 ORCHESTRATION SURFACE (judgments / capabilities / 事实 schema / resolver / exprBuilder /
ledger / disciplines / 任一 workflows SKILL.md) 求交集,机械得出 requires_second_opinion。
基准是上一个 release tag,不是 merge-base origin/main —— 后者在 commit-即-push-main
的纪律下塌缩成 HEAD,只看得见未提交改动,会漏掉多-commit milestone 的早期 commit。
算不出来 (无 tag / 无 git / diff 失败) 时取 false,并在每轮 <workflow-state> 断点打出
SECOND-OPINION: 判据不可用(<原因>)。不乱 fire,且不静默。
Capability refs
Sister workflows/capabilities.yaml entries:
codex— 第二意见 / cross-AI peer review via codex (impl: gstack, cmd: /codex)
Gate ref
Sister workflows/judgments/stage-routing.yaml:
verify-second-opinion-orchestration.fires—phase.stage == 'verify' and requires_second_opinion == true
Routing rules
- ✅ 触发: 本次改动触及编排契约本身 (judgments / capabilities.yaml / phaseFactContext / facts.ts / judgmentResolver / exprBuilder / ledger.ts / disciplines / 任一 SKILL.md)
- ❌ 跳过: 纯 installer / 文档 / 测试 / 依赖 bump —— 改这些不会改变引擎的决策方式
交付物即证据。 本 sub fire 了就必须交 second-opinion.md;不交则 checkpoint complete
fail-closed 阻断,--force 在 ledger 记 evidence_status: overridden。跳过因此是台账上
一行,不是隐形的。
How to invoke
!harnessed checkpoint intent verify-second-opinion
The banner above (when present) means this invocation is REGISTERED with the engine (an intent marker) — not yet compliant: the steps below (prompt → spawn → checkpoint complete) resolve it, and a per-turn
<workflow-intent>reminder persists until they run.
The numbered sequence below is the state machine — execute it with Bash. Do NOT improvise an equivalent flow from the Overview above: freelancing bypasses the engine (no ledger, no evidence guard). harnessed gives you the spawn-ready prompt; YOU spawn the subagent with a {{ host.native }} {{ host.spawn_subagent }} (keeps the session responsive + lets clarification round-trips reach the user).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -1 lines 68cbeae05119
- 2mo ago First seen · 90 lines · 100 tokens per session scan A 3bb07898be26
verify-second-opinion is a skill published in the GitHub repository easyinplay/harnessed (2 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,539 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
security-architecture-review
Reviews a design or change for security before it ships — authentication and authorization, data handling, secrets, dependencies, and the secure-development practices around it. Use this to review an architecture or pull request for security, set secure coding standards, choose or tune SAST and DAST tooling, assess a…
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.