An autonomous build command that takes a software task through planning, discussion, approval, implementation, testing, code review, and finalization.

It helps load project context, create and debate an implementation plan, retrieve relevant code, implement the task, run tests, and review the result.

It organizes the full development cycle and adds a user approval point before implementation. This helps catch planning problems before code is changed.

build — Command by dr-code

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.

agentmods

npx agentmods add commands/dr-code/tessera/build

Clone the repo

git clone --depth 1 https://github.com/dr-code/tessera

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 942 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.00942
Opus 5	$0.00013	$0.00471
Sonnet 5	$0.00005	$0.00188
Haiku 4.5	$0.00003	$0.00094

Measured yesterday against content hash 0944f52eb9fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

commands/build.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/build — Autonomous Build Loop

Task: $ARGUMENTS

Full pipeline: load context → GPT initial plan → Claude+GPT debate → user approval gate → implement → test → GPT code review → finalize.

Phase 0: Load Context

Read CLAUDE.md in the project root (skip silently if missing)
Read docs/PROJECT_CONTEXT.md (skip silently if missing)
If tessera MCP is active:
- Call graph_continue with the task as query
- If needs_scan=true, run graph_scan first
- Read all recommended_files via graph_read
Record the user's exact task as acceptance criteria

Phase 1: GPT Plans

Send the task and project context to Codex for an initial plan:

codex exec "You are a senior engineer. Create a detailed implementation plan for: $ARGUMENTS. Project context: <CONTEXT>. Output: (1) files to create or modify with rationale, (2) implementation approach per file, (3) correct ordering of steps, (4) edge cases to handle, (5) risks. Be specific — name actual files and functions."

If tessera is active, call graph_retrieve with key terms from the plan to surface relevant existing code.

Phase 2: Claude Debates GPT's Plan

Claude critiques the plan: architecture fit, project conventions, edge cases, ordering problems. Then send critique to Codex:

codex exec "Plan revision for: $ARGUMENTS. Your original plan: <GPT_PLAN>. Claude critique: <CRITIQUE>. Output a revised plan that addresses each critique point. Keep what was correct, fix what was wrong."

Produce a final agreed plan from the debate output.

Phase 3: User Approval Gate

Present the final plan via AskUserQuestion. Include:

Task summary and acceptance criteria
Files to create or modify
Implementation approach
Resolved debate points
Open risks

Do NOT write any code until the user explicitly approves.

If tessera MCP is active, call plan_save with project_name, subtask_name, task=$ARGUMENTS, and plan_markdown=<approved plan> to register the plan for compliance tracking.

Read the full file on GitHub · 94 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.

yesterday First seen · 94 lines · 25 tokens per session scan A 0944f52eb9fe

Subscribe to this mod's changes

build is a command published in the GitHub repository dr-code/tessera (1 stars, last pushed 21d ago), licensed MIT. It adds 25 tokens to every session and 942 once invoked, about $0.0001 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 2026-08-31.

Code review Planning Testing

build

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/build — Autonomous Build Loop

Phase 0: Load Context

Phase 1: GPT Plans

Phase 2: Claude Debates GPT's Plan

Phase 3: User Approval Gate

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement