goal

goal is a command for coding agents from fockus/skill-memory-bank. It costs 12 tokens per session (617 once invoked), scanned A, original, MIT.

A command that creates and checks two durable project files: `goal.md` for the desired outcome and acceptance criteria, and `project.md` for lasting constraints.

In plain words
What is it for?
Use it to create missing goal and project templates and validate that the goal contains the information needed to judge completion.
Why use it?
It gives an automated workflow a clear end condition and the project rules it must respect.

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/fockus/skill-memory-bank/goal
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank

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 goal

README.md
[![agentmods](https://agentmods.dev/badge/commands/fockus/skill-memory-bank/goal.svg)](https://agentmods.dev/commands/fockus/skill-memory-bank/goal)
Your own site
<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/goal"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/goal.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 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 $0.00012 $0.00617
Opus 5 $0.00006 $0.00309
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 4d ago against content hash dcf780d5a86c, 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 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.

commands/goal.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mb goal

Scaffold the Dynamic Flow goal primitive — the durable goal.md (end-state + ## Acceptance criteria, the deterministic termination condition) and project.md (slow-changing non-negotiable constraints read at flow start) — then validate the goal.

Phase-1 scope: scaffold + validate only. The full /goal lifecycle (status | init | set | done | list) is out of scope here and lands in a later phase. This command does NOT pick a route or run a flow.

What it does

  1. Resolve the active Memory Bank (scripts/_lib.sh::mb_resolve_path).
  2. If .memory-bank/goal.md is absent, copy templates/goal.md to it and tell the user which fields to fill (id, ## Description, ## Acceptance criteria, and progress_source). Never overwrite an existing goal.md.
  3. If .memory-bank/project.md is absent, copy templates/project.md to it so the slow-changing constraints exist for flow start (REQ-DF-002). Never overwrite an existing project.md.
  4. Validate the goal with scripts/mb-goal-validate.sh. A valid goal exits 0 with {"ok":true}; an invalid one exits 1 and prints a concrete fix-hint per problem on stderr (missing acceptance, missing/unresolvable progress_source, or mode: adaptive without replan_with).

goal.md stays durable-only — no live check-results, no route/phase fields. Per ADR-5 those ephemeral runtime fields live in the <!-- mb-flow --> fence inside status.md, so the acceptance aggregator can grep goal.md for - [x]/N without fence noise.

Usage

# Scaffold both artifacts if absent, then validate the goal.
SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"   # memory-bank skill bundle root
BANK=".memory-bank"

[ -f "$BANK/goal.md" ]    || cp "$SKILL_DIR/templates/goal.md"    "$BANK/goal.md"
[ -f "$BANK/project.md" ] || cp "$SKILL_DIR/templates/project.md" "$BANK/project.md"

bash "$SKILL_DIR/scripts/mb-goal-validate.sh" "$BANK/goal.md"

Run it before starting a goal-driven flow. Fix any hint the validator prints, then re-run until it exits 0.

Read the full file on GitHub · 57 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 First seen · 57 lines · 12 tokens per session scan A dcf780d5a86c

Subscribe to this mod's changes

goal is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 617 once invoked, about $0.0001 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 2026-08-30.