Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add umangbuilds/dhurandhar-os/plugin install dhurandhar-osWrote 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/skills/umangbuilds/dhurandhar-os/builder)<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/builder"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/builder"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00246 | $0.03887 |
| Opus 5 | $0.00123 | $0.01944 |
| Sonnet 5 | $0.00049 | $0.00777 |
| Haiku 4.5 | $0.00025 | $0.00389 |
Grade C, and why
builder scanned grade C with 1 finding 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf` (anywhere outside `.tmp/`, `node_modules/`, `__pycache__/`, build artifacts). How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder
Builder is the TDD-first implementation orchestrator. The operator says "build the disbursement webhook" — Builder writes the plan first, the failing test second, the implementation third, and hands off to Reviewer fourth.
The discipline is the moat. Builder enforces it.
When this skill activates
Builder owns spec-to-code, not raw build intent. The split with workflow-orchestrator:
- Raw build intent ("I want to build X", "let's build Y", "create a tool that Z", "I have an idea for Q") → workflow-orchestrator fires first, walks the operator through reality-check → PRD → build → review → launch, and only then hands off to Builder.
- Spec-to-code ("implement the spec," "build per the PRD," "code this up based on the spec," "let's code," "write the function for X in the spec," "ship the spec," "implement Y from the PRD") → Builder fires directly.
Auto-trigger conditions:
- Spec-aware phrases: "implement the spec," "build per the PRD," "code this up," "code this up based on the spec," "let's code," "ship the spec," "write the function for [X in the spec]," "implement [Y from the PRD]."
- Concrete implementation phrases when a PRD or locked spec exists in the working directory or session: "write the function," "create the endpoint," "make a CLI for," "wire up the integration."
- Any edit operation targeting a path containing
.env,prod.config, orproduction. - Direct invocation by workflow-orchestrator after the PRD checkpoint (
build).
Explicit invocation: "use builder to implement X."
Does NOT activate on:
- Raw build intent without a spec (workflow-orchestrator owns this — see its triggers).
- Spec writing (PRD Writer), code review (Reviewer), brainstorming (Idea Reality Check), deployment architecture (Deployment Advisor).
Spec presence check. Before responding to an ambiguous "build X" / "let's code" message, look for a PRD signal: a file named prd.md / spec.md / PRD.md / SPEC.md / *.prd.md in the working directory, OR a spec produced earlier in this session, OR an explicit operator reference to a prior spec ("the PRD we wrote yesterday"). If a spec signal is present, Builder fires. If not, yield to workflow-orchestrator.
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.
- 10d ago First seen · 273 lines · 246 tokens per session scan C 621f60066854
builder is a skill published in the GitHub repository umangbuilds/dhurandhar-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 246 tokens to every session and 3,887 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.