Trace Harness Launch Failure

Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retrying both runners.

ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not fou...

Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.

After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.

Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gat...

Consolidate traces into the persistent wiki (WikiSkill).

Propose skills from wiki patterns and traces (WikiSkill).

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Use when you need to resolve an in-progress git merge/rebase conflict.

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold e...

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests,...

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

A relentless interview that asks every frontier question at once, round by round.