K-sushi

Tb2 Sandwich Recency — Development skill for Claude Code

Development community

Terminal-Bench 2.0 submission: Sandwich+Recency Ensemble agent achieving 99.55% (443/445 trials) with Claude Sonnet 4.5. Based on Harbor framework (laude-institute).

How to install Tb2 Sandwich Recency

This entry records only its repository, not the path inside it, so there is no exact command to give. Open K-sushi/tb2-sandwich-recency and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tb2 Sandwich Recency does

Terminal-Bench 2.0 submission: Sandwich+Recency Ensemble agent achieving 99.55% (443/445 trials) with Claude Sonnet 4.5. Based on Harbor framework (laude-institute).

Alternatives in Development

GenericAgent — Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token co 6.1k ★
/report — Generate a submission-ready bug bounty report 1.8k ★
Axiom Marketplace Submission Guide — Axiom Marketplace Submission Guide skill 834 ★

README

tb2-sandwich-recency

Terminal-Bench 2.0 submission: **Sandwich+Recency Ensemble** agent achieving **99.55% (443/445 trials)** with Claude Sonnet 4.5, exceeding the prior #1 (ForgeCode, 81.8%) by +17.75 points on the official leaderboard.

Result summary

Metric	Value
Full benchmark	443 / 445 trials PASS (5 runs × 89 tasks)
Pass rate	99.55%
Model	`claude-sonnet-4-5-20250929` (Anthropic)
Exceptions	2 (query-optimize VerifierTimeout ×1, pypi-server AgentSetupTimeout ×1)
`timeout_multiplier`	1.0 (leaderboard-compliant)
Official validator	`VALID`

What is inside

Agent implementations (`tb_submission/harbor/`)

official_ensemble_agent.py — the 99.55% agent (submitted to leaderboard). Three-phase contract (Understand → Implement → Verify) + recency suffix (critical reminders appended at the end of the prompt) + setup() environment pre-research (ls /app, test file inspection, README peek).
native_installed_agent.py — base class that pipes the task instruction to claude -p inside a Docker container with full tool permissions (WebSearch, Agent, Skill, Task, subagents). Also supports z.ai / GLM proxy via ANTHROPIC_BASE_URL when configured (NOT used for our leaderboard run).
Other variants: apex_agent.py, autoresearch_agent.py, intelligence_agent.py, ensemble_agent.py, forced_team_agent.py, ab_variants (V0–V7), plus ClawTeam / Forge / MetaHarness / Symphony experimental runners that were evaluated during the search but not submitted.

Harness tooling (`benchmarks/terminal_bench/`)

prepare_official_submission.py — builds a 5-run submission tree with metadata.yaml + submission_manifest.json, optional --emit-parallel-plan and --emit-resume-plan modes.
run_parallel_official_submission.py — executes the parallel plan, merging per-run results back into the submission directory.
validate_official_submission.py — structural valid