agentmods.dev

of-builder

of-builder is an agent for Claude Code from william-london/ownframework-loop. It costs 37 tokens per session (4,009 once invoked), scanned A, original, Apache-2.0.

A specialized engineering agent that implements or repairs one approved work unit inside a prepared OwnFramework Loop worktree. A worktree is an isolated checkout of a repository.

In plain words
What is it for?
It is for carrying out one assigned build or repair pass and returning a result for the parent coordinator to review.
Why use it?
It keeps each build pass tied to the coordinator’s approved inputs and prevents the agent from changing the project’s authoritative process records.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the of-loop plugin — 5 skills, 2 agents, 2 hooks shipped together

not rated 0repo changed 24d ago A scan 37 tokens original Apache-2.0

Good fit It is for carrying out one assigned build or repair pass and returning a result for the parent coordinator to review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/william-london/ownframework-loop/of-builder
View source ↗ william-london/ownframework-loop ownframework.com
Install

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.

Clone the repo
git clone --depth 1 https://github.com/william-london/ownframework-loop

Made for: Claude Code.

Or install of-loop, the plugin that ships this one along with the rest of its 5 skills, 2 agents, 2 hooks.

Wrote 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.

agentmods badge for of-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/william-london/ownframework-loop/of-builder/github.svg)](https://agentmods.dev/agents/william-london/ownframework-loop/of-builder)
Your own site
<a href="https://agentmods.dev/agents/william-london/ownframework-loop/of-builder"><img src="https://agentmods.dev/badge/agents/william-london/ownframework-loop/of-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.

agentmods 80×15 button for of-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/william-london/ownframework-loop/of-builder"><img src="https://agentmods.dev/badge/agents/william-london/ownframework-loop/of-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.04009
Opus 5.5 $0.00015 $0.01604
Sonnet 5.5 $0.00007 $0.00802
Haiku 4.5 $0.00004 $0.00401

Measured 24d ago against content hash 2839307f5889, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

of-builder scanned grade A with 2 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 24d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

networking (raw `curl` / `wget` / Python `requests` / direct

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`subprocess.run`) launches the commissioned broker outside
agents/of-builder.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

of-builder

You are the fresh engineering executor for exactly one claimed build pass.

The parent /of-loop:build coordinator already ran ofloop build claim, ofloop build prepare, and ofloop build agent-skeleton. Do not reconstruct protocol values.

Required prepared inputs

Your prompt must provide:

  • canonical_repo
  • run_id
  • worktree
  • branch
  • baseline_sha
  • cp_id (PROGRAM mode; empty for SINGLE)
  • work_unit_id
  • repair_round
  • packet_sha256
  • approval_sha256
  • agent_result_path
  • checkpoint_id and acceptance_criterion_ids when supplied
  • repair_context when the current pass repairs a CHANGES_REQUESTED verdict

If any required value is missing, stop and tell the parent. Do not invent it. For an initial build, repair_context may be null. For a repair pass it is deterministic transport from one of two authoritative sources, named by repair_context.source_kind:

  • review_verdict — copied from the exact prior authoritative REVIEW_VERDICT.json (failed acceptance results, findings, validation evidence, failure reason, reviewed SHA).
  • build_receipt — copied from the authoritative BUILD_RECEIPT.json when the deterministic build finalizer itself routed the run back to CHANGES_REQUESTED (required validation failures, scope/protected/secret findings) without a fresh review verdict.

Authority

You may write only:

  1. source/config/test files inside the exact supplied builder worktree, subject to the approved packet paths/budgets; and
  2. the exact supplied pass-scoped semantic artifact: .ownframework-loop/<run-id>/scratch/builder/pass-<NNNN>/BUILD_AGENT_RESULT.json.

You may NOT write WORK_PACKET.md, APPROVAL.json, STATE.json, BUILD_RECEIPT.json, REVIEW_VERDICT.json, EVENTS.log, STOP, or LOCK. You may not choose/create/remove worktrees, choose branches/baselines, approve, push, merge, deploy, publish, create remotes, or perform external effects.

Governed public research (only if the packet authorizes it)

Read the full file on GitHub · 348 lines

Changes

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.

  1. 24d ago Changed · +15 lines 2839307f5889
  2. 1mo ago Changed · +41 lines 2010496bcb6f
  3. 1mo ago Changed · +89 lines 842281d0869f
  4. 1mo ago Changed · +6 lines dfd6eeb63bf7
  5. 1mo ago Changed · +5 lines 0f770a910231
  6. 1mo ago Changed · +6 lines bbd035500076
  7. 1mo ago Changed · +8 lines 3f4e86d0e8d0
  8. 1mo ago First seen · 178 lines · 37 tokens per session scan A f12f9aebf53d

Subscribe to this mod's changes

of-builder is an agent published in the GitHub repository william-london/ownframework-loop (0 stars, last pushed 16d ago), licensed Apache-2.0. It adds 37 tokens to every session and 4,009 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewGit and workflowPythondeveloper-toolshuman-in-the-loopsoftware-engineering
Related

Other agents, from other repositories

ase-repo-review

Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of Git changes — the way a thorough reviewer would judge a pull request before approving it.

rse/ase · 7 tokens

commit-pusher

Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.

MarcusJellinghaus/mcp-tools-py · 27 tokens

release-validator

Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.

rlajous/claude-code-commands · 25 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

reviewer

Use proactively to review code for correctness, security, and quality against the kit rules. Read-only; reports findings by severity with file:line evidence.

mnzralee/claude-multi-agent-architecture · 33 tokens

devops-engineer

The DevOps Engineer maintains build pipelines, CI/CD configuration, version control workflow, and deployment infrastructure. Use this agent for build script maintenance, CI configuration, branching strategy, or automated testing pipeline setup.

tranhieutt/software_development_department · 45 tokens