Grant Reviewer — Development agent for Claude Code
Adversarial per-category grant-rubric reviewer for /mos:grade-grant's reviewer-panel examination mode -- examines ONE rubric category in isolation, then (as the ruling consolidator) renders the holist.
How to install Grant Reviewer
Installs to ~/.claude/agents/jsagir-mindrian-os-plugin-grant-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jsagir/mindrian-os-plugin/HEAD/agents/grant-reviewer.md -o ~/.claude/agents/jsagir-mindrian-os-plugin-grant-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Grant Reviewer does
name: grant-reviewer description: Adversarial per-category grant-rubric reviewer for /mos:grade-grant's reviewer-panel examination mode -- examines ONE rubric category in isolation, then (as the ruling consolidator) renders the holistic verdict across all seven. model: inherit color: blue allowed-tools:
- Read
- Glob hitl_shape: "F.8" hitl_why: "The seven rubric categories (eligibility/process/budget/legal/reporting/market/ip) are examined as an independent panel in any order, an unorder
Alternatives in Development
- Chain Executor — Executes delegated chain steps with context isolation 186 ★
- Surface Auditor — Checks that every published surface still describes this binary — site prose, README, FEATURES, CHANGELOG/BACK 96 ★
- Unit Tester — Specialist in logic isolation and unit testing 93 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Thales Reviver
Thales Explorer persona. Re-examines a specific ruled-out direction with current ledger context to determine w
R4 Sculptor
Reinforced Suite 4 Sculptor for the Suite Cascade System. Sculpture, bidirectional examination, multi-angle co
Matcher
Score each queued role 0-100 against the profile using the scoring rubric; pick a resume category; flag inelig
Code Quality Critic
Adversarially reviews a code change through the single CODE-QUALITY lens (rubric lens 2) and emits a critic-sc
Correctness Critic
Adversarially reviews a code change through the single CORRECTNESS lens (rubric lens 1) and emits a critic-sch
Judge Panel
Use when a draft or a past winning entry must be scored against a contest's official rubric before submission.
Related Skills
Id Concept Render
让 AI 生成审美在线、结构保真、有创新点的工业设计概念图 / Fix ugly AI product renders: a SKILL.md workflow with six-layer prompts, a rev
Muse:Debate
Run a 3-round adversarial debate between two personas on a question. Round 1 is opening statements, Round 2 is
05 Verification Panel
<!-- Injected: {{ANGLE}} {{ANGLE_QUESTION}} {{TARGETS_JSON}} {{PAPER_TXT_PATH}} {{STAGED_SOURCES_DIR}} {{QUOTE