Not in the top 1,000 by GitHub stars
dadwadw233/claude-code-harness
Claude Code-inspired harness blueprint skill for designing agent runtimes.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/claude-code-harness/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9dfe1c027189 → 9dfe1c027189
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9dfe1c027189
No earlier version was observed for comparison.
Verified commit 9dfe1c0271895933825b9f64af13a16d484c5f33
git clone --filter=blob:none --no-checkout https://github.com/dadwadw233/claude-code-harness.git .hotskills/dadwadw233-claude-code-harness && git -C .hotskills/dadwadw233-claude-code-harness checkout --detach 9dfe1c0271895933825b9f64af13a16d484c5f33
# Copy each selected skill directory from .hotskills/dadwadw233-claude-code-harness into .claude/skills/<skill-name>/Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- claude-code-harness
skills/claude-code-harness
How it works
claude-code-harness
When your agent uses it
Design a real harness for an agentic system using Claude Code-inspired patterns. Use when the user needs a harness blueprint, request assembly design, execution loop, tool runtime, memory layering, permission model, transcript or recovery strategy, or wants to turn a vague agent idea into a harness-level architecture. Do not use for generic product brainstorming, simple prompt writing, or isolated code generation.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,080 tokensWhen the skill is activated
Reference documents
1,783 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What to optimize for
- Output contract
- Workflow
- Anti-patterns
- Style guidance
- References
Files
../../.claude-plugin/marketplace.jsonasset562 bytes../../.claude-plugin/plugin.jsonasset397 bytesLICENSE.txtdoc1,028 bytesSKILL.mdcore5,224 bytesagents/openai.yamlasset270 bytesreferences/claude-code-derived-insights.mddoc2,332 bytesreferences/harness-blueprint-template.mddoc1,366 bytesreferences/harness-pattern-language.mddoc2,294 bytesreferences/harness-principles.mddoc2,377 bytes
Read SKILL.md
# Claude Code Harness
Design the harness, not just the agent prompt.
This skill helps turn an agent idea into a harness blueprint that specifies:
- how a turn is assembled
- how the execution loop runs
- how tools are governed
- how memory survives boundaries
- how permissions and recovery are enforced
- how the system stays understandable to humans
## What to optimize forSkills included
- claude-code-harness
Repository facts
- License
- MIT
- Created
- Mar 31, 2026
- Last pushed
- Apr 5, 2026
- Forks
- 1
- Open issues
- 1
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
- No broad tool permissions
- No dangerous shell commands
- 4 network referencesin 1 file: .claude-plugin/plugin.json:7
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 4 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"email": "dadwadw233@users.noreply.github.com" }, "homepage": "https://github.com/dadwadw233/claude-code-harness", - Network accessline 8
}, "homepage": "https://github.com/dadwadw233/claude-code-harness", "repository": "https://github.com/dadwadw233/claude-code-harness", - Network accessline 9
"homepage": "https://github.com/dadwadw233/claude-code-harness", - Network accessline 10
"repository": "https://github.com/dadwadw233/claude-code-harness",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/claude-code-harness/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/claude-code-harness/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/claude-code-harness/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/claude-code-harness/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/claude-code-harness/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
