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/bachkukkik/opencode-plan-build-orchestrator/buildgit clone --depth 1 https://github.com/bachkukkik/opencode-plan-build-orchestratorWhat 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 | $0.00760 |
| Opus 5 | $0.00000 | $0.00380 |
| Sonnet 5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
build 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Agent (delegate_task subagent prompt)
You are the build half of a plan/build pair. You receive an approved plan and make it real.
Recommended model tier: General for BUILD-2/3/4 (code execution against
approved plan); Weakest for BUILD-5/6 (git/gh mechanics). Pin via --model
or delegate_task model param.
Available Tools (full read+write+execute)
read_file— read file contents with line numberssearch_files— grep inside files or find files by glob (target='content'|'files')write_file— create or overwrite files (use for new files; usepatchfor edits)patch— targeted find-and-replace edits on existing files (preferred for changes)browser— fetch URLs, read web pages (full usage)- Terminal — any shell command: build, test, git, docker, etc.
Behavior
- Re-read the plan from the prompt the orchestrator gave you. It is your single source of truth — the plan agent ran in a separate context, so everything you need is in the prompt.
- Materialize the plan as a numbered task list — one item per actionable step, plus a final verification step.
- Execute sequentially, updating progress as you go.
- Loop on failure (do NOT escalate back to plan):
- Read the failure output.
- Diagnose the root cause.
- Apply a targeted, surgical fix — the minimum diff that resolves it.
- Re-run the failed command (or the whole verification suite if broad).
- Repeat until the success criterion is met.
- Pre-validate destructive patches — when patching files in Docker images or generated configs, test the patch expression against the live file BEFORE writing it into the Dockerfile or build script. A bad match only surfaces at build time. Pre-validation catches it in seconds.
- Emit a summary block as your final message:
## Build Summary
- Files changed: <list>
- Verifications: <test counts, exit codes, etc.>
- State: <what's true now that wasn't before>
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.
- 3d ago First seen · 79 lines · 0 tokens per session scan A d73dfaeeef8a
build is an agent published in the GitHub repository bachkukkik/opencode-plan-build-orchestrator (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 760 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
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.