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 agentmods add skills/firatcand/forge/second-opinionnpx skills add firatcand/forge --skill second-opiniongit clone --depth 1 https://github.com/firatcand/forgeWrote 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/firatcand/forge/second-opinion)<a href="https://agentmods.dev/skills/firatcand/forge/second-opinion"><img src="https://agentmods.dev/badge/skills/firatcand/forge/second-opinion.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.01978 |
| Opus 5 | $0.00045 | $0.00989 |
| Sonnet 5 | $0.00018 | $0.00396 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/second-opinion
Preconditions
.forge/settings.yamlexists andagents.review_host_cliis set to a host that DIFFERS from the primary —claude,codex, orgemini(notnull). FORGE-224:claudeis a valid review host (it reviews viaclaude -p, metered against the Agent SDK credit pool — see ORCHESTRATOR.md §Phase 2).- The configured reviewer CLI is installed (
which claude/which codex/which gemini). - Working tree is rebased onto current
main. The reviewer reads files from disk; if the worktree is stale, the reviewer reasons about old code and may miss recently-merged dependencies (sibling adapters, new abstractions, refactored APIs). Alwaysgit fetch origin main && git rebase origin/mainin the worktree before invoking. - For framework projects using gitignored project meta (e.g.,
spec/,plans/,docs/learnings/): re-hydrate them in the worktree after rebase so the reviewer sees the canonical source-of-truth, not just the tracked source files.
Why a second opinion (not just an in-CC agent)
The reviewer runs in a separate process with its own context, its own model, and its own training cutoff. It has no memory of this conversation. That makes it an honest second opinion: it can't be primed by what you've already concluded, and it'll catch type errors / mirror-faithfulness bugs that an agent inheriting context will rationalize away.
Two things to leverage:
- Codebase reasoning. The reviewer reads the working tree on demand (
rg,sed, file reads). It can trace a tracker's dependency on a sibling adapter, check a refactor against recently-merged PRs, verify a plan's pseudocode against the actual type signatures it claims to mirror. - Plan + code together. The strongest reviews compare a written plan against the production code it will modify. Brief the reviewer on both — point to the plan file AND the source files it touches AND the sibling/precedent files it mirrors.
Invocation (via forge orchestrate second-opinion)
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.
- 5d ago First seen · 124 lines · 90 tokens per session scan A 5ccf63cd89f5
second-opinion is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,978 once invoked, about $0.0005 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 skills, from other repositories
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.
submit-pr
Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.
prospec-explore
Explore - Requirement exploration, problem investigation, and solution comparison partner. Triggers: explore, compare, investigate, unsure, clarify, 探索, 比較, 釐清, 調查, 不確定.
prospec-plan
Plan Implementation - Convert User Story into technical implementation plan (plan.md) and change specification (delta-spec.md). Triggers: plan, architecture, technical plan, 規劃, 架構規劃, 技術規劃.
prospec-knowledge-update
Incremental Knowledge Update - Parse delta-spec.md to identify affected modules, scan source code, and update module README, index.md, and module-map.yaml incrementally. Triggers: knowledge update, incremental update, sync knowledge, update docs, 更新知識, 增量更新, 同步知識, 更新文件.