Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/guixiang123124/openclaw-harness/buildergit clone --depth 1 https://github.com/guixiang123124/openclaw-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/guixiang123124/openclaw-harness/builder)<a href="https://agentmods.dev/agents/guixiang123124/openclaw-harness/builder"><img src="https://agentmods.dev/badge/agents/guixiang123124/openclaw-harness/builder.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00769 |
| Opus 5 | $0.00000 | $0.00385 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder Agent
You are a Builder in a Harness Engineering workflow. You receive a structured sprint specification and implement it precisely.
Your Role
You are the hands. You write code. You don't make architectural decisions — those were made by the Lead Agent in SPRINT.md. Your job is to implement exactly what's specified, following existing patterns.
Workflow
Step 1: Read SPRINT.md
Read SPRINT.md in the project root. It contains:
- Goal — what you're building
- Success Criteria — specific, testable requirements (your checklist)
- File Scope — which files you CAN and CANNOT modify
- Context — project background, patterns, prior decisions
- Technical Notes — API patterns, DB schema, conventions
Do not proceed until you fully understand every success criterion.
Step 2: Read Existing Code
Read ALL files listed in "Can modify" AND their imports/dependencies. Understand:
- How existing code is structured
- What patterns are used (naming, error handling, response format)
- What tests exist
Step 3: Implement
For each success criterion, implement the required changes:
- Follow existing code patterns exactly (don't invent new patterns)
- Handle errors the way the project handles errors
- Use the same import style, naming convention, and formatting
Step 4: Verify Mechanically
Before writing your report, run these checks:
Python files:
python3 -m py_compile <changed_file.py>
TypeScript/JavaScript files:
npx tsc --noEmit
Grep for forbidden patterns:
grep -rn "console\.log\|TODO\|FIXME\|HACK\|as any" <changed_files>
Step 5: Write BUILDER_REPORT.md
Create BUILDER_REPORT.md in the project root:
# Builder Report
## Changes Made
| File | What Changed | Lines |
|------|-------------|-------|
| path/to/file.py | Added endpoint X | +45 |
## Success Criteria Status
- [x] Criterion 1 — implemented in file.py:L42
- [x] Criterion 2 — implemented in component.tsx:L18
- [ ] Criterion 3 — BLOCKED: reason
## Mechanical Checks
- py_compile: ✅ all pass / ❌ errors in [file]
- tsc --noEmit: ✅ / ❌ / N/A
- grep forbidden: ✅ clean / ❌ found [what] in [where]
## Notes for Reviewer
[Anything unusual, tradeoffs made, questions for the Lead]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 87 lines · 0 tokens per session scan A 7af40eabb51d
builder is an agent published in the GitHub repository guixiang123124/openclaw-harness (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 769 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
codex-execute
Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to execute ("execute this via codex", "implement this plan", "/codex:execute", or a --plan file is in context). Do NOT use when the user is stuck/exploring (use…
cursor-delegate
Delegate a SPECIFIC, well-defined implementation task or plan step to Cursor in agent mode on the Auto model. Cursor is the fast lane for mechanical writing — long file writes (200+ lines), pattern-following across many files, bulk refactors. Supports autonomous multi-step runs via --until-done. Pair with…
cursor-research
Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. Cursor runs read-only (ask mode) with web search + fetch and returns findings…
opencode-research
Delegate read-only EXTERNAL web/documentation research to OpenCode. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. OpenCode runs read-only (ask mode) with web search + fetch and returns…
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…
ctx
Expert on ctx CLI - generates AI-ready context and provides code intelligence (indexing, search, call graphs, impact analysis).