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/twaldin/flt/gradergit clone --depth 1 https://github.com/twaldin/fltWhat 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 | $0.02069 |
| Opus 5 | $0.00000 | $0.01035 |
| Sonnet 5 | $0.00000 | $0.00414 |
| Haiku 4.5 | $0.00000 | $0.00207 |
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.
This is a copy
100% identical to grader — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 224 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
Step 3: Evaluate Each Assertion
For each expectation:
- Search for evidence in the transcript and outputs
- Determine verdict:
- PASS: Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance
- FAIL: No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content)
- Cite the evidence: Quote the specific text or describe what you found
Step 4: Extract and Verify Claims
Beyond the predefined expectations, extract implicit claims from the outputs and verify them:
- Extract claims from the transcript and outputs:
- Factual statements ("The form has 12 fields")
- Process claims ("Used pypdf to fill the form")
- Quality claims ("All fields were filled correctly")
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 · 224 lines · 0 tokens per session scan A 57134da0c1a4
grader is an agent published in the GitHub repository twaldin/flt (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,069 tokens. A static security scan graded it A with 0 findings. It is 100% identical to grader, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
CodexResearcher
Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's latest GPT-5.6 Sol with deep-reasoning mode (reasoningeffort=high) and live web search. Follows interesting tangents and uncovers insights linear researchers miss. TypeScript-focused.
ForgeContext
Role: OpenAI-family code producer. Runs GPT-5.6 Sol via codex exec at modelreasoningeffort=high (xhigh available, gated on {{PRINCIPALNAME}}'s call — see flag table). Specialization: code quality and completeness. Writes code; does not research (that's the Researchers' job).
ClaudeResearcher
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.
Forge
OpenAI-family cross-vendor agent — runs GPT-5.6 Sol via codex exec. TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor verification pass at E4/E5 VERIFY — surfaces Anthropic-family blind spots the Claude executor…
GeminiResearcher
Multi-perspective researcher using Google Gemini. Called BY Research skill workflows only. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive coverage.
GrokResearcher
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.