Command Grader — Development agent for Claude Code
Grades command execution transcripts against assertion definitions (standard, hard-gate, contract).
How to install Command Grader
Installs to ~/.claude/agents/harshanandak-forge-command-grader.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/harshanandak/forge/HEAD/.claude/agents/command-grader.md -o ~/.claude/agents/harshanandak-forge-command-grader.md Restart Claude Code, or start a new session, for it to be picked up.
What Command Grader does
name: command-grader description: Grades command execution transcripts against assertion definitions (standard, hard-gate, contract)
Command Grader Agent
You are a strict grader that evaluates command execution transcripts against a set of assertions. You receive a transcript of an agent's command execution and a list of assertions to check. Your job is to determine whether each assertion passes or fails based solely on the evidence in the transcript.
Input
You will receive:
1.
Alternatives in Development
- Memory Extractor Agent — You extract perception changes from Claude Code session transcripts - the "aha moments" where understanding sh 3.6k ★
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
- Engram Assessor — Independent grader of learner productions for the Engram learning plugin 1.4k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Skill Eval Grader
스킬 eval 용 채점자 — 러너 결과를 assertion 리스트로 채점하고 엄격한 JSON 판정을 반환한다. 채점과 동시에 assertion 품질(변별력) 자체도 비평한다. skill-creato
P2a Acceptance Reviewer
Independently judges executed functional behavior evidence against the active iteration Gate B contract.
Worker Validator
Black-box runtime validator (#256). Given a PR + its validation-contract.md, RE-RUNS each assertion's command
Holdings Valuation Scorer
Grades the valuation of one ETF's holdings, assessing P/E, P/B, and EV multiples against industry averages, ea
Contract Reviewer
Reviews API changes for contract breaks. Given git diff of API definitions and existing consumer pacts, classi
Sdd Cross Auditor
Cross-references all 9 SDD skill definitions for I/O contract mismatches, version inconsistencies, and stale c
Related Skills
Cleaning Pass
Stage 2 cleaning pass - watermark/artifact removal via the detect -> gate -> mask -> LaMa inpaint -> verify lo
Plan Check
You are now a task list completeness checker. Run hard-gate checks against the input tasks.json and output whe
Q Status
Check Spec-Kit-Plus workflow status with Quality Gate grades - shows phase progress, validation reports, and n