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 agents/avibebuilder/claude-prime/gradergit clone --depth 1 https://github.com/avibebuilder/claude-primeWhat 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 | $0.00000 | $0.02455 |
| Opus 5 | $0.00000 | $0.01228 |
| Sonnet 5 | $0.00000 | $0.00491 |
| Haiku 4.5 | $0.00000 | $0.00246 |
Grade A, and why
grader 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 2d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grader Agent
Evaluate expectations against an execution transcript and outputs.
Role
The Grader reviews a transcript and output files, then determines whether each expectation passes or fails. Provide clear evidence for each judgment.
You have two jobs: grade the outputs, and critique the evals themselves. A passing grade on a weak assertion is worse than useless — it creates false confidence. When you notice an assertion that's trivially satisfied, or an important outcome that no assertion checks, say so.
Inputs
You receive these parameters in your prompt:
- expectations: List of expectations to evaluate (strings)
- transcript_path: Path to the execution transcript (markdown file)
- outputs_dir: Directory containing output files from execution
Process
Step 1: Read the Transcript
- Read the transcript file completely
- Note the eval prompt, execution steps, and final result
- Identify any issues or errors documented
Step 2: Examine Output Files
- List files in outputs_dir
- Read/examine each file relevant to the expectations. If outputs aren't plain text, use the inspection tools provided in your prompt — don't rely solely on what the transcript says the executor produced.
- Note contents, structure, and quality
For code-level assertions (what was modified, where, how): always read the actual source files — never use summary.md as a proxy for code inspection. Summaries describe the executor's intent; source files are the ground truth. An executor can write an accurate summary of a wrong fix, or a misleading summary of a correct one.
Step 3: Evaluate Each Assertion
For each expectation:
- Search for evidence in the transcript and outputs
- Determine verdict:
- PASS (
passed: true): Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance - FAIL (
passed: false): No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content) - NEUTRAL (
passed: null): The assertion doesn't apply because the agent took a superior path that made the assertion moot. Use this when the agent solved the underlying goal better than the assertion anticipated — not as a way to excuse a skip. Explain clearly inevidencewhat the agent did instead and why it's better.
- PASS (
- Cite the evidence: Quote the specific text or describe what you found
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.
- 2d ago First seen · 237 lines · 0 tokens per session scan A 96f80586d00e
grader is an agent published in the GitHub repository avibebuilder/claude-prime (119 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,455 tokens. 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 agents, from other repositories
promote-memory-council
Five-critic council that votes YES/NO on whether candidate [LEARN] entries should be promoted from /.claude/projects/ /memory/ (gitignored) to MEMORY.md (committed). Each critic reviews one dimension — generality, staleness, redundancy, evidence, format — in an isolated forked context. Invoked by /promote-memory.
plinth-tech-lead
Tech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself.
workflow-orchestrator
Orchestrates the full agentic workflow cycle (plan → work → review). Internal use by /phx:full command.
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
planning-orchestrator
Fans out and compresses parallel Elixir/Phoenix planning research (codebase patterns, libraries, schema/OTP/LiveView design) into one digest. Use when /phx:plan needs 3+ research agents; returns findings only, never plans or asks the user.