A product-management command that proposes the next release plan from collected signals and current project state. The plan covers the release goal, feature candidates, technical debt, scope limits, autonomy levels, and a Devil's Advocate review.

Use it after harvesting signals to define the release thesis, evaluate features, reserve work for technical debt, identify items to remove, and check whether the project needs stabilisation.

It turns scattered feedback and project information into a concrete proposal for what the next release should contain.

shape — Command by dormstern

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/dormstern/forge/shape

Clone the repo

git clone --depth 1 https://github.com/dormstern/forge

Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,145 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	$0.00072	$0.01145
Opus 5	$0.00036	$0.00573
Sonnet 5	$0.00014	$0.00229
Haiku 4.5	$0.00007	$0.00114

Measured yesterday against content hash 24b6cd860060, 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 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/shape.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:shape — Release shaping (PM mode) — HERO COMMAND

Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.

You propose a release plan. This is the magic moment of Forge. The output of /forge:shape is what the user screenshots and shares.

Pre-conditions

HARVEST is complete: releases.json.current_cycle.signals has entries.
IDENTITY.md, architecture.md, and features.json all exist and are current.

Behavior

Read state. releases.json (signals + last 2 releases), IDENTITY.md, architecture.md, features.json. Do not skip any.
Propose a release plan with these sections:
- Thesis (1 sentence): what this release is about.
- Identity evolution (only if signals warrant): trigger + rationale + risk. The user owns IDENTITY.md changes — propose, don't write.
- Feature candidates: each with signal_id, requested_by, intent (1–2 sentences), autonomy (T1/T2/T3), and depends_on.
- Debt paydown (~15% of scope): pull from features.json tech_debt items.
- Kill list (≥10% of scope — the 10% Delete Rule): features with post_mvp_status: "evaluate", low-usage signals, or stale work. If nothing qualifies, state it explicitly with evidence — don't skip.
- Contract implications (if contract_mode != "none"): per-API breaking change risk.
- Appetite: what's explicitly NOT in this release.
- Stabilization check: auto-fire if rework_rate > 15% OR blocked_features ≥ 3 OR avg_resets > 2 OR avg_quality_score < 6.0 across last 5. If any trigger, recommend a stabilization release (all debt + rework, zero new features).
Auto-dispatch devils-advocate against the proposed plan. Surface the top 2–3 attacks inline in the shape output. The user can run /forge:falsify for harder attacks.
Render the hero card in monospace with Unicode borders. ✓/⚠/✗ markers. Columns: feature name, autonomy tier, signal id. Sections: features, debt paydown, kill list, DA findings.

Read the full file on GitHub · 81 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 · 81 lines · 72 tokens per session scan A 24b6cd860060

Subscribe to this mod's changes

shape is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,145 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.

Code review Git and workflow Planning

shape

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/forge:shape — Release shaping (PM mode) — HERO COMMAND

Pre-conditions

Behavior

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement