shape

An interview tool for turning ideas, discussions, code, specifications, or tasks into a shared, detailed understanding. It asks all currently answerable questions in rounds and does not write implementation code.

In plain words
What is it for?
Use it to examine meeting transcripts, understand older code without documentation, find gaps in an existing specification, or refine an issue until it can be implemented directly.
Why use it?
It exposes missing decisions, unclear requirements, and hidden assumptions before development begins. This reduces the need for an agent or developer to guess.

Command

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/w00fx/spec-anchored-agentic-development/shape
Clone the repo
git clone --depth 1 https://github.com/w00fx/spec-anchored-agentic-development
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,330 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 $0.00078 $0.02330
Opus 5 $0.00039 $0.01165
Sonnet 5 $0.00016 $0.00466
Haiku 4.5 $0.00008 $0.00233

Measured 2d ago against content hash 02ec43af5a29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shape 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 2d 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.

commands/shape.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identify the target from the argument and pick the mode:

  • An idea or ongoing discussion → interview toward a capability spec (/to-spec writes it).
  • A transcript (meeting, chat, voice note) → extract what was decided, interrogate the gaps.
  • Existing code with no spec (brownfield) → archaeology: read the code, establish what it does, interrogate what it should do.
  • An existing spec → grill-back: interrogate the document for ambiguity and holes (/to-spec applies the refinements).
  • A task / issue → sharpen it until an agent could implement it without guessing.

All modes are one machine: interview relentlessly until the frontier is empty and we reach a shared understanding — every branch of the design tree visited, nothing left silently assumed; that is the termination condition, not a checklist filled. Never write implementation code — and never write or edit the spec file: that is /to-spec's job.

Interview mechanics

  • Map the interview as a design tree and work it in rounds. Every decision branches into the decisions that hang off it. The frontier is every question whose prerequisites are already settled — askable now without guessing at answers you haven't heard. Ask the whole frontier in one round, numbered; then wait. A question whose answer depends on another question still open in this round belongs to a later round. Each round of answers reshapes the tree — settled decisions push the frontier outward; recompute and ask the next round.
  • For each question, provide your recommended answer. The human confirms or corrects; composing from scratch is friction. The recommendation is a proposal — the human's answer is the truth.
  • If a question can be answered by exploring the codebase, explore the codebase instead — dispatch the exploration and don't block the frontier on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait; ask the rest of the round now. One law bounds this (our addition, for domains where truth is external): code settles facts ("the parser already returns a validated Decimal"); code does not settle intent — behavior found in code enters as a question, never as a rule, until the human confirms. Code can contain bugs that became structural.
  • Numbers before prose. For any calculation or threshold rule: collect the input → expected-output pairs with the human FIRST, then draft the EARS rule as the generalization of agreed examples. In the reverse order, examples get invented to fit your wording — you end up validating your prose, not their truth.
  • Stay inside one capability. If the work crosses capability boundaries, stop and say so — that is architecture (new contracts, the human-led route), not a spec interview.

Read the full file on GitHub · 194 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. 2d ago First seen · 194 lines · 78 tokens per session scan A 02ec43af5a29

Subscribe to this mod's changes

shape is a command published in the GitHub repository w00fx/spec-anchored-agentic-development (5 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 2,330 once invoked, about $0.0004 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.