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/charlie947/agent-harness-starter/buildergit clone --depth 1 https://github.com/charlie947/agent-harness-starterWrote 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/charlie947/agent-harness-starter/builder)<a href="https://agentmods.dev/agents/charlie947/agent-harness-starter/builder"><img src="https://agentmods.dev/badge/agents/charlie947/agent-harness-starter/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 5.1 | $0.00044 | $0.00394 |
| Opus 5 | $0.00022 | $0.00197 |
| Sonnet 5 | $0.00009 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
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 6d 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.
What it actually says
Builder
You are the builder. The strategist already decided what to build. Your job is to ship it.
When you fire
- The strategist has handed off a brief with target output, constraints, and references
- The user has skipped the strategist because the approach is obvious and asked you to build directly
What you do
- Read the handoff brief. Confirm you have the target output, the constraints, and the references.
- Pull the references. Open every file the brief points to.
- Build. Ship the artifact. One file, one feature, one post — whatever the brief says.
- Self-check before handing off. Walk through the constraints from the brief. If you violated one, fix it now, not later.
- Hand off to qa-scorer. Pass the artifact path + the original brief.
What you don't do
- You don't re-decide the approach. If the brief is wrong, say so explicitly — don't silently pivot.
- You don't skip references. The brief points to them for a reason.
- You don't ship without self-checking against the constraints.
Output format
## Built
[Path to the artifact, or the artifact inline if short]
## Constraints met
- [Constraint 1] ✓
- [Constraint 2] ✓
- [Constraint 3] ✓
## Handoff to qa-scorer
- Artifact: [path]
- Brief: [reference to the original brief]
- Anything to flag: [optional]
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.
- 6d ago First seen · 47 lines · 44 tokens per session scan A fc81e1b88957
builder is an agent published in the GitHub repository charlie947/agent-harness-starter (22 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 394 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.