It is shown that borderline task difficulty is agent-specific (Spearman rho=0.75), offering a candidate explanation for prior contradictions: single-agent studies draw tasks from different agents'informative bands.
Abstract
Persistent context files (AGENTS.md, CLAUDE.md) are standard practice for guiding AI coding agents, yet evidence for their effectiveness is contradictory. We present a controlled ablation of context-injection strategy across two frontier agents (Claude Code and Codex), 17 real tasks from 3 repositories (15 shared + 2 Codex-only), and 288 evaluated runs with gold-test evaluation. Context strategy does not measurably move correctness on either agent (bounded to<=10-15pp via equivalence testing). A failure-mode triage reveals why: agents fail on implementation skill---feature design, pattern selection, exact wiring---not missing repository knowledge that a context file could supply; a manipulation probe confirms the real AGENTS.md never converts a near-miss to a pass on either agent. We further show that borderline task difficulty is agent-specific (Spearman rho=0.75), offering a candidate explanation for prior contradictions: single-agent studies draw tasks from different agents'informative bands. We release all code, data, and analysis.
Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters. We run the missing crossed comparison: an integrity-clean three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks, holding model, harness, and prompts fixed, with two agents (Claude Code, OpenAI Codex CLI) so the comparison spans both regime and agent-design axes. Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival in three cells (significantly on Artifact/Claude and SWE-bench/Codex; directionally on Artifact/Codex), with pass rates statistically tied within each cell. The lone exception is SWE-bench/Claude, where code_only is directionally costlier (+14.4%, not significant); a conditional-cost analysis localizes that gap to failure-cost on doomed-run trajectories, not a per-edit tax on successful runs. Two implications: the cheapest tool surface is jointly determined by task regime and agent design rather than by either axis alone, and the headline cost signal lives in cache-adjusted cost -- not pass rate, which is invariant across surfaces at the model sizes we evaluate. The benchmark harness, task suite, and analysis code are available at https://github.com/hyang0129/onlycodes.
These findings recast a matched Skill as a hypothesis about a particular Skill-project-model triple rather than a portable asset, reframing injection as a per-deployment routing decision and making length-matched controls and per-model audits a minimum standard for Agent-Skill evaluation.
A deterministic routing stress test over 20,000 skills shows the functional impact: skills with valid routing metadata are retrieved more reliably from startup descriptions than skills with routing defects, while AI-marked skills show more safety and portability problems.
Chi Zhang, Yimin Liu, Xinze Chen et al.· 0 citations
These findings establish context measurement as a validated preflight signal for agent reliability and position context engineering as an auditable layer of agent evaluation and governance.
This work provides a bounded failure classification and empirical case study for white-box code auditing, and varies the surrounding context and classify where failures first become visible: lost requirements, editing drift, failed checking, or non-agent evaluator/runtime failures.
This work formalizes minimum-sufficient execution and the Agent Cognitive Redundancy Ratio (ACRR), and proposes E3 (Estimate, Execute, Expand): the agent estimates an initial operating point, executes a minimum viable path, and expands scope only when verification fails.
J. Yin, Xinyu Feng· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
