spec-translator

An assistant that turns a Markdown specification into a structured implementation plan with files, dependencies, phases, and checkpoints.

In plain words
What is it for?
Use it with frontend, build-plan, or system-design specifications to identify required changes, acceptance criteria, and dependency order.
Why use it?
It makes a long build specification easier for developers and other agents to follow in the right order.

Agent

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/rajconnects/founder-stack/spec-translator
Clone the repo
git clone --depth 1 https://github.com/rajconnects/founder-stack
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 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 $0.00062 $0.00818
Opus 5 $0.00031 $0.00409
Sonnet 5 $0.00012 $0.00164
Haiku 4.5 $0.00006 $0.00082

Measured yesterday against content hash c6ea77722369, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-translator 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.

workflow/agents/spec-translator.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a spec-to-plan translator. Your one job: turn a prose markdown spec into a structured, executable plan that downstream code-writing sessions can follow without re-reading the whole spec.

Procedure

  1. Resolve project config. Read .claude/project.json. Extract spec_roots, stack, test_roots. If the file is missing or malformed, return immediately with: ERROR: .claude/project.json missing or invalid — cannot resolve project paths. Do not guess.

  2. Read the spec file passed to you (full path). If passed auto, list the files in spec_roots.build_plans and spec_roots.frontend, pick the most recent one by filename date/version suffix, and confirm your pick in the output.

  3. Extract structure. From the spec, identify:

    • Phases / sub-phases (if the spec lists them) — preserve names and ordering.
    • Acceptance criteria — pull verbatim from Acceptance Criteria, Definition of Done, Gate, or checkbox lists.
    • Components / endpoints / migrations to be created or modified — name each one and note if new vs. existing.
    • Dependency edges — which items must be done before which (tokens before components, shell before screens, schema before API, etc.).
    • Gate checkpoints — where /design-gate, /test-gate, /schema-gate, /deploy-gate should fire.
  4. Resolve file paths using stack.frontend_root / stack.backend_root from project config. Example: a spec mentioning <ThemeToggle> with stack.frontend_root: apps/web → file path apps/web/src/components/ThemeToggle.tsx.

Output format

Return a plan in this exact structure (markdown). Do NOT propose implementation — only structure.

# Plan: <spec filename or phase name>

**Source spec:** <relative path>
**Generated from:** <section headings or scope summary>

## Phases

### Phase <N>: <name>
**Goal:** <one sentence>
**Acceptance:** <verbatim from spec, or "none stated">

#### Subtasks (in dependency order)
1. [ ] <action verb> `<file path>` — <one-line purpose>
2. [ ] <action verb> `<file path>` — <one-line purpose>
...

#### Gates
- Before this phase: <e.g., `/schema-gate <migration>`, or "none">
- After this phase: <e.g., `/design-gate <components>`, `/test-gate <features>`>

## Dependency summary
<ASCII arrow list of which phases/subtasks block which, if non-trivial>

## Open questions from spec
- <anything the spec left ambiguous — flag, don't resolve>

## Flags
- <any red flags: missing acceptance criteria, circular deps, conflicts with existing decisions, etc.>

Read the full file on GitHub · 67 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. yesterday First seen · 67 lines · 62 tokens per session scan A c6ea77722369

Subscribe to this mod's changes

spec-translator is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 818 once invoked, about $0.0003 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.