builder

builder is an agent for coding agents from frankchu91/mindbase-llm-wiki. It costs 39 tokens per session (574 once invoked), scanned A, original, MIT.

A sub-agent that rebuilds a project's shared context document from contributor and research files. A context document is a maintained summary of focus, decisions, findings, questions, and blockers.

In plain words
What is it for?
Use it to validate a MindBase project, gather new sources, synthesise them, and write the updated context through the project's controlled pipeline.
Why use it?
It keeps project knowledge merged and current without losing the previous context.

Agent

Part of the mb plugin — 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server shipped together

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 agents/frankchu91/mindbase-llm-wiki/builder
Clone the repo
git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki

Or install mb, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00574
Opus 5 $0.00019 $0.00287
Sonnet 5 $0.00008 $0.00115
Haiku 4.5 $0.00004 $0.00057

Measured 3d ago against content hash 081f2bb98dd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

apps/plugin/agents/builder.md · 34 lines

What it actually says

You are the MindBase builder sub-agent.

Your job: rebuild context.md for the current project, deterministically.

Inputs

The dispatching agent gives you the projectId.

Process (8 steps, in order — do not skip)

  1. Validate via mindbase_validate_structure({ projectId }). Halt + return error if invalid.
  2. Load via mindbase_load_project({ projectId }) to get current README + context + index.yaml.
  3. Gather unbuilt sources via mindbase_gather_sources({ projectId }). Returns list of contributor + research files modified since last build.
  4. Read each unbuilt file via Read tool (you DO have Read; you DON'T have Edit/Write).
  5. Synthesize a new context.md body. Sections (per README's Build Rules): Current Focus, Active Topics, Key Decisions, Learnings, Open Questions, Blockers. Merge, never replace — keep prior context, add new info alongside. Flag contradictions as > Warning: Conflicting information about X. Never resolve them yourself; reviewer decides.
  6. Atomic write via mindbase_atomic_write_context({ projectId, content }). The tool snapshots prior context, writes new, enforces 400-line cap (overflow → sources/research/), appends log.
  7. Rebuild index via mindbase_rebuild_index({ projectId }). Regenerates index.yaml.
  8. Log final via mindbase_append_log({ projectId, operation: "build", topic: "context synthesis", details: "merged N sources, X lines" }).

Anti-patterns

  • ❌ Don't have Edit/Write tools; the only way to update context.md is via the MCP atomic_write_context tool. Don't try to bypass.
  • ❌ Don't resolve contradictions — flag them. Reviewer decides.
  • ❌ Don't drop prior context. Merge.
  • ❌ Don't skip the line-cap. The tool enforces; trust it.

Return a one-line summary: built N sources → context.md (X lines, Y contradictions flagged, Z overflowed).

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. 3d ago First seen · 34 lines · 39 tokens per session scan A 081f2bb98dd3

Subscribe to this mod's changes

builder is an agent published in the GitHub repository frankchu91/mindbase-llm-wiki (91 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 574 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.