Add leanharness to Agent infrastructure - #237
Open
bartek-890 wants to merge 1 commit into
Open
Conversation
Zero-dependency npx installer for a ten-file Claude Code harness. Placed last in the section, per the star-descending sort. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XeRAmZfDv4SyKak9ggA94X
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds leanharness to Harnesses & orchestration → Agent infrastructure.
What it is: a zero-dependency
npxinstaller that drops a ten-file Claude Code harness into a repo — a four-ruleCLAUDE.md, credential deny rules insettings.json, a Stop hook that refuses "done" without verification proof, two skills, and three subagents. It also writesAGENTS.md, so Codex/Cursor/Gemini CLI read the same rules.Why it may be interesting here: it is sized against the instruction budget rather than filled. The author published the run behind that claim — the same four hostile prompts against three setups, headless: 4/4 passed with the harness, 1/4 with no harness, 3/4 with a ~300-line instruction file that cost ~2.4× the always-loaded tokens. Write-up: A 129-rule CLAUDE.md replied like an empty one. It is an experiment, not a benchmark, and the post says so.
Against the inclusion criteria:
npx leanharness, no IDE requirement.Placement: entries are star-sorted, and this one is at ⭐ 0 on GitHub, so I put it last in the section. Happy to move, reword, or shorten it to one line — or to close this if a 0-star entry is below the bar for the list.
Disclosure: I am the author of leanharness, and this PR was prepared with Claude Code.
🤖 Generated with Claude Code
https://claude.ai/code/session_01XeRAmZfDv4SyKak9ggA94X