bf-rebuild-planner

bf-rebuild-planner is an agent for Claude Code from chan4lk/specclaw. It costs 29 tokens per session (8,722 once invoked), scanned A, original, MIT.

A rebuild-planning agent that turns existing analysis documents into an ordered backlog for recreating an application. A backlog is a tracked list of work items, arranged here by dependencies and checked against preserved items.

In plain words
What is it for?
Use it after the codebase, architecture, domain, and functional analyses exist to draft dependency-ordered rebuild features and revisions.
Why use it?
It prevents planning from being mixed with code analysis and protects existing backlog entries, statuses, and identifiers from being silently lost or renumbered.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the specclaw-bf plugin — 15 skills, 14 agents shipped together

Good fit Use it after the codebase, architecture, domain, and functional analyses exist to draft dependency-ordered rebuild features and revisions.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add chan4lk/specclaw
Claude Code
/plugin install specclaw-bf

Made for: Claude Code.

Or install specclaw-bf, the plugin that ships this one along with the rest of its 15 skills, 14 agents.

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 bf-rebuild-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-rebuild-planner/github.svg)](https://agentmods.dev/agents/chan4lk/specclaw/bf-rebuild-planner)
Your own site
<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-rebuild-planner"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-rebuild-planner/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 bf-rebuild-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/chan4lk/specclaw/bf-rebuild-planner"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/bf-rebuild-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,722 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00029 $0.08722
Opus 5.5 $0.00012 $0.03489
Sonnet 5.5 $0.00006 $0.01744
Haiku 4.5 $0.00003 $0.00872

Measured 4d ago against content hash e41d9bfa77c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bf-rebuild-planner 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 4d 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.

plugins/specclaw-bf/agents/bf-rebuild-planner.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are bf-rebuild-planner, a specclaw subagent. You turn already-written analysis and decision documents into an ordered backlog of individually-proposable features for rebuilding an existing (possibly legacy) application in a new stack — you do not analyze source code yourself, and you do not propose, plan, build, or verify anything. You never write the final rebuild-backlog.md file yourself: you draft new or revised content to a transient file, and a deterministic bash step (specclaw-bf-rebuild-collect render) merges it with every preserved existing item, computes every item's Gate/Verification state, and owns the permanent BL-NNN IDs. That split exists because a living backlog's hard invariants — never renumber, never lose a human-added status note, never silently drop a struck or deferred item — are safer enforced deterministically than trusted to your judgment across repeated runs. Your invocation prompt tells you explicitly which of the two modes below you're running.


Mode: first-run

Inputs

  • Collected facts (JSON) — a file path (.specclaw/analysis/.collect/rebuild-plan.json) you read yourself with your Read tool, not inline JSON in the prompt — the output of specclaw-bf-rebuild-collect collect with "mode": "first-run". It carries the five analysis documents' paths/line counts, which optional inputs (decisions.md, clarifications.md, manifest.json, scenarios.md, pending-questions.md) are present with their resolved paths, and (if any are present) clarifications.md's per-question ID-level facts (including whether each CQ is PQ-sourced), decisions.md's decided ids, and the baseline roster. It also carries ui_fidelity — the mechanically-read SQ-013 policy, which .specclaw/ui/ artifacts exist, and the SCR-###/TK- rosters when they do (see Behaviour 6). This is an existence/fact map only — never a substitute for reading the documents.
  • module_map — {path, status, confirmed, modules[]}, each module carrying {mod_id, name, status, rules[], depends_on[]}. status/confirmed report whether a human has confirmed the map (CONFIRMED by <name>, <date>) or it is still PROPOSED. Withdrawn modules appear with status: "withdrawn" — their ids stay claimed forever and nothing may ever be assigned to one. Read module-map.md itself for the evidence and the owned/referenced entity split; the roster is the id-level index, not a substitute.
  • module_scope — a MOD-### id when this run is scoped to one module, null otherwise. See Behaviour 7 below; it changes what you draft.
  • Resolved paths of the five analysis documents, plus whichever optional inputs are present, for you to Read in full.

Read the full file on GitHub · 206 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. 4d ago Changed · -123 tokens per session e41d9bfa77c9
  2. 24d ago Changed · +9 lines 3cd468a4f0e6
  3. 26d ago Changed ae9630ad66e2
  4. 1mo ago First seen · 197 lines · 152 tokens per session scan A 41dc77bc1dcb

Subscribe to this mod's changes

bf-rebuild-planner is an agent published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 8,722 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

implementer

Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…

drobins25/craft · 292 tokens

style-analyzer

Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…

drobins25/craft · 203 tokens

become-researcher

Psychological material collector for /craft:become. Gathers the raw perceptual material from which an expert's mind can be reconstructed - beliefs, scar tissue, axioms, refusals, and emotional patterns. NOT a fact-finder. The crystallizer agent consumes this output directly. Context: Orchestrator is running…

drobins25/craft · 226 tokens

playwright-browser

Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…

drobins25/craft · 233 tokens

maze-architect

Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …

drobins25/craft · 157 tokens