fable-goal-cycle

fable-goal-cycle is a skill for Claude Code, Codex from synaptent/aragora. It costs 106 tokens per session (1,267 once invoked), scanned A, original, MIT.

A bounded planning cycle that packages repository and recent agent activity, asks Claude Fable 5 to rank goals, and executes one suggested prompt.

In plain words
What is it for?
It is for choosing the next development goal, creating a one-cycle plan, and producing a paste-ready prompt for the next task.
Why use it?
It turns a large ongoing mission into a reviewable next step while recording the gathered context and response.

Skill for Claude CodeCodex

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 skills/synaptent/aragora/fable-goal-cycle
Any agent
npx skills add synaptent/aragora --skill fable-goal-cycle
Clone the repo
git clone --depth 1 https://github.com/synaptent/aragora

Made for: Claude Code, Codex.

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 fable-goal-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptent/aragora/fable-goal-cycle.svg)](https://agentmods.dev/skills/synaptent/aragora/fable-goal-cycle)
Your own site
<a href="https://agentmods.dev/skills/synaptent/aragora/fable-goal-cycle"><img src="https://agentmods.dev/badge/skills/synaptent/aragora/fable-goal-cycle.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,267 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 5.1 $0.00106 $0.01267
Opus 5 $0.00053 $0.00633
Sonnet 5 $0.00021 $0.00253
Haiku 4.5 $0.00011 $0.00127

Measured 5d ago against content hash e7526076342b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fable-goal-cycle 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 5d 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.

.agents/skills/fable-goal-cycle/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fable Goal Cycle (adaptive mission loop)

One command mechanizes the loop digest → packet → consult → next prompt:

python3 scripts/fable_goal_cycle.py \
  --goal "Standing mission statement, one or two sentences" \
  --json

What it does, all bounded:

  1. Package — snapshots live state (origin/main SHA, branch status, open non-draft PRs, open epics, worktrees, recent docs/plans, and the last 24h of agent activity via scripts/agent_session_digest.py --all). Every source has its own short timeout; failures become a "context gaps" section in the packet instead of aborting, so Fable knows what it is not seeing.
  2. Consult — sends the packet to Claude Fable 5 through the bounded consult tool (consult_claude.py, resolved from repo scripts/ or ~/.codex/skills/consult-fable/), default 900s timeout, demanding a fixed response format: ## ASSESSMENT, ## NEXT GOALS (max 3, ranked), ## NEXT PLAN (one cycle only), ## NEXT PROMPT (one fenced paste-ready prompt).
  3. Emit — persists packet.md, response.md, next_prompt.md under .aragora/goal_cycles/<timestamp>/ (gitignored) and prints the next prompt (or a JSON envelope with --json).

Goal-ranking durability filter: prefer goals whose output is a durable standard — something that takes frontier judgment to WRITE but only ordinary intelligence to APPLY (charters, rubrics, playbooks, skills, checkers). Test: could a cheaper model redo this artifact tomorrow? If yes, rank it lower.

Wrong-hill disclosure: before ranking goals, if the standing mission metric itself is the wrong hill — mis-specified, superseded by events, or clearly worse than an adjacent goal — the consult is expected to say so FIRST in a dedicated 'WRONG HILL' section with one-paragraph evidence, and propose the better goal. Misalignment disclosure is invited and costs nothing; grinding a bad metric costs cycles.

Useful flags: --dry-run (build the packet only — inspect it before spending a consult), --context-file <path> (repeatable; include a redacted cycle report or steering note only after placing it under .aragora/goal-cycle-context/), --since-hours 48, --skip-digest, --timeout 1200, --model claude-opus-5.

Exit codes: 0 ok, 2 consult failed/timed out, 5 response lacked a ## NEXT PROMPT block (raw response is still saved).

Read the full file on GitHub · 96 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. 5d ago First seen · 96 lines · 106 tokens per session scan A e7526076342b

Subscribe to this mod's changes

fable-goal-cycle is a skill published in the GitHub repository synaptent/aragora (11 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,267 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens