goal

A planning command for turning an approved specification into structured goals or ordered task groups. P.O.V.E.R. means Problem, Outcome, Validation, Execution, and Risks.

In plain words
What is it for?
Use it to draft goals from a specification, create a goal manually, list existing goals or task groups, or inspect one by ID.
Why use it?
It makes the intended result, checks, dependencies, owners, and risks explicit before implementation begins. It also works across hosts that may not provide a native goal command.

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/lookatitude/guild/goal
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 717 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 $0.00056 $0.00717
Opus 5 $0.00028 $0.00358
Sonnet 5 $0.00011 $0.00143
Haiku 4.5 $0.00006 $0.00072

Measured 2d ago against content hash 461680348369, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goal 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/goal.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guild:goal - P.O.V.E.R. goal and task-group surface

Creates or inspects planning goals. A goal is P.O.V.E.R.-structured: Problem, Outcome, Validation, Execution, Risks. The command is a Planning surface, not an implementation shortcut: it can draft goals or task groups, but Build still requires the approved plan gate.

When the host supports a native /goal command, Guild maps the same guild.goal.v1 body to the host-native surface. /guild:goal remains the portable Guild surface across hosts. When goal support is unavailable or inappropriate, Planning emits guild.task_group.v1: ordered verifiable tasks with dependencies, validation, owner/team, project scope, and acceptance criteria traceability.

Usage

/guild:goal from-spec <slug>
/guild:goal new <slug>
/guild:goal list
/guild:goal show <goal-id>

Args & local flags

  • from-spec <slug> - read .guild/spec/<slug>.md or a guild.define.v1 source and draft goals/task groups for approval.
  • new <slug> - create a manually authored P.O.V.E.R. goal draft.
  • list - list goals/task groups known to the current plan or initiative.
  • show <goal-id> - show one goal or task group and its traceability.

All global flags apply. --dry-run prints the proposed goal/task artifacts and writes nothing.

Gates

  • Goal/task approval I
  • Plan approval I before Build
  • Initiative attach/create I when the broad-work trigger fires

Broad-work trigger: multi-project work, two or more goals, more than six tasks, or expected multi-session delivery. The trigger proposes an initiative; it never silently attaches.

Output artifact

One of:

  • guild.goal.v1 - P.O.V.E.R. goal preserving acceptance-criteria ids.
  • guild.task_group.v1 - ordered fallback task group preserving dependencies, validation, team ownership, project scope, and acceptance-criteria ids.

The artifacts feed /guild:plan; they do not bypass team composition, plan-review, or plan approval.

Dispatch

Resolve the active Planning phase and current spec/define artifact, then:

Read the full file on GitHub · 78 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 · 78 lines · 56 tokens per session scan A 461680348369

Subscribe to this mod's changes

goal is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 717 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.