claude-forge: Skill for Claude Code

.claude/skills/forge-graded-verify/SKILL.md

forge-graded-verify is a skill for Claude Code from ForgeyClap/claude-forge. It costs 45 tokens per session (752 once invoked), scanned A, original, MIT.

A review method that scores the quality of research, retrieval-based answers, scraped data, or predictions against a written rubric. Retrieval-augmented generation, or RAG, means answers built from retrieved source material.

In plain words
What is it for?
Use it for high-stakes answer reviews, with criteria such as source grounding and answer quality. It is advisory and does not block irreversible actions.
Why use it?
Basic checks can confirm that a process finished but cannot judge whether the answer is well supported or useful.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ForgeyClap/claude-forge's own configuration. It tells Claude Code how to work on claude-forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-forge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ForgeyClap/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ForgeyClap/claude-forge/main/.claude/skills/forge-graded-verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code.

Wrote 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.

agentmods badge for forge-graded-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-graded-verify.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-graded-verify)
Your own site
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-graded-verify"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-graded-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00752
Opus 5 $0.00023 $0.00376
Sonnet 5 $0.00009 $0.00150
Haiku 4.5 $0.00005 $0.00075

Measured 7d ago against content hash 80b1ce158ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge-graded-verify 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 7d 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.

.claude/skills/forge-graded-verify/SKILL.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge-graded-verify — advisory rubric-scored verification (scout #7, 2026-07-13)

Fills the graded-quality axis Forge deliberately lacks: forge-verify checks structural bookkeeping ("did the agent close its tickets"); forge-evals is intentionally deterministic-binary so it can safely gate git reverts. Neither scores subjective ANSWER QUALITY. This skill adds that — advisory only. Method reimplemented from the DeepVerifier failure-taxonomy pattern (arXiv 2601.15808); no code/dataset from that repo is used.

When to use

High-stakes answer-quality work where "did it pass an assertion" isn't enough: RAG answers, research syntheses, scraped-data summaries, prediction rationales. NOT for code/build gating (that stays with forge-evals + integration-gate). Reserve for genuinely high-stakes tasks — it costs an LLM review pass; don't duplicate ultra-review.

How it works (advisory, bounded, never gates irreversible actions)

  1. Pick the rubric for the domain from .claude/config/rubrics/<domain>.json. Each criterion has: id, descriptor (4-level: 1=poor … 4=excellent, what each level means), and raise (what would move the score up).
  2. Dispatch review-boss as a GRADED verifier (not the binary reviewer): it reads the output + the source/context, and returns per-criterion {id, score 1-4, evidence, feedback} via verification-by-decomposition (judge each criterion separately, cite evidence).
  3. Bounded single rework loop: if any required criterion scores < the threshold (default 3), emit ONE rework_task_createdrework_assigned to the owning Boss with the NL feedback, re-grade ONCE, respect the usage-guard. No open-ended loops.
  4. Log advisory only: record the graded result via the existing gate_evaluated / lead_review_completed events (do NOT invent event types). NEVER let a graded score gate an irreversible action (deploy, git revert, send) — deterministic forge-evals / owner approval stay authoritative there.

Honesty

LLM-graded scores are judgment, not ground truth (a judge can mislabel). Frame results as advisory quality signals; cite per-criterion evidence; the reviewer model should differ from the builder model (evaluator independence). Rubrics are owner-editable JSON — start from the shipped ones and ADAPT per project, don't drop-in.

Read the full file on GitHub · 24 lines

Changes

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.

  1. 7d ago First seen · 24 lines · 45 tokens per session scan A 80b1ce158ca6

Subscribe to this mod's changes

forge-graded-verify is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 752 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

ai-search-optimization

Use when building or auditing a site for SEO visibility in AI Overviews, AI Mode, or generative search (AEO / GEO / answer-engine optimization), or when someone asks how to "optimize for ChatGPT/Gemini/AI search", whether to add llms.txt or AI text files, how grounding / query fan-out / RAG pick pages, indexability…

S3YED/appie-kit · 119 tokens

knowledge-pipeline

Operate the local-first Weblyfe knowledge pipeline for ingesting documents and workspace content, embedding locally, semantic search, and graph exploration.

S3YED/appie-kit · 31 tokens

knowledge-query

Hybrid search (vector + BM25 via RRF + metadata boost) against the pgvector Knowledge base, with optional RAG synthesis. Use when the user asks factual questions that should be grounded in indexed documents (e.g., 'what do we know about X', 'search the knowledge base for Y', '@knowledge '). Pass answer=true to…

evolution-foundation/evo-nexus · 85 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

FluxonLab/Skillry · 37 tokens

hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

FluxonLab/Skillry · 35 tokens

langchain-architecture

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

FluxonLab/Skillry · 45 tokens