1.5 KiBLFS
1.5 KiBLFS
Harnesses research
Source-level audits of how coding-agent harnesses (claude-code, opencode, openhands, codex, pi, and others) discover, surface, and invoke agent skills.
Files
skill-invocation-surfaces.md— how each harness exposes skills to the model: tool call vs. prompt injection, frontmatter recognition vs. agentskills.io spec, trajectory auditability, permission scoping, lifecycle, and re-rank delta vs. earlier audits. Verified 2026-05-03 against current source.
Evidence (hosted, not committed)
Trajectory artifacts referenced by these audits live on HuggingFace under
benchflow/skillsbench-research-artifacts.
Each zip contains the full ACP trajectory JSONL, install log, verifier output,
reward, config, and prompts for one task run.
| File | Task | Harness | Model | Date |
|---|---|---|---|---|
openhands-exoplanet-detection-period-2026-05-03.zip |
exoplanet-detection-period |
OpenHands CLI 1.15.0 (sdk 1.17.0) | claude-sonnet-4-6 | 2026-05-03 |
Method
Each row in skill-invocation-surfaces.md is grounded in either:
- Direct quotation of upstream source (file path + commit/branch noted), or
- Direct quotation of authoritative docs (URL noted), or
- An ACP trajectory we ran on a public SkillsBench task and archived above.
Where a source has gone private or moved (e.g. pi-mono), the row is flagged needs reverification.