fable-validate-fableplan

fable-validate-fableplan is a skill for Claude Code from richkuo/rk-skills. It costs 62 tokens per session (1,540 once invoked), scanned A, original, MIT.

A workflow that checks a GitHub issue with Fable 5, corrects its description when needed, and posts an implementation plan. Fable 5 is the specified planning model.

In plain words
What is it for?
Use it when you want an issue validated and planned for later implementation. It accepts an issue URL, issue number, repository issue reference, or no issue.
Why use it?
It helps ensure the plan is based on verified issue details instead of inaccurate or incomplete claims, while stopping before any code is built.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the rk-skills plugin — 37 skills, 1 command shipped together

Good fit Use it when you want an issue validated and planned for later implementation. It accepts an issue URL, issue number, repository issue reference, or no issue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richkuo/rk-skills/fable-validate-fableplan
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.

Any agent
npx skills add richkuo/rk-skills --skill fable-validate-fableplan
Clone the repo
git clone --depth 1 https://github.com/richkuo/rk-skills

Made for: Claude Code.

Or install rk-skills, the plugin that ships this one along with the rest of its 37 skills, 1 command.

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-validate-fableplan

README.md
[![agentmods](https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-fableplan/github.svg)](https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-fableplan)
Your own site
<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-fableplan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fable-validate-fableplan

Your own site · 80×15
<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-fableplan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00062 $0.01540
Opus 5 $0.00031 $0.00770
Sonnet 5 $0.00012 $0.00308
Haiku 4.5 $0.00006 $0.00154

Measured 7d ago against content hash 3197386f6bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fable-validate-fableplan 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 7d 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.

skills/fable-validate-fableplan/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fable-validate-fableplan

Chain fable-validate → (conditional) update issue → fableplan into one autonomous run, and stop there: Fable 5.1 validates the issue, the main agent fixes the issue description if needed, and Fable 5.1 plans the implementation. The vetted plan is posted to the issue as a comment. Nothing is built.

This is fable-validate-fableplan-loop with the implementation stage removed — the head of that chain is identical (same validation, same scope gate, same issue edits, same unconditional Fable plan), but the handoff to work-on-issue-loop is dropped. Reach for this when you want the issue fact-checked, corrected, and planned so a human (or a later run) can decide what to do with the plan. When the plan should be built and driven through review in the same run, use fable-validate-fableplan-loop instead.

Do not skip or reorder the chain. Validation gates planning; a plan built on refuted claims is wrong. There is no sanctioned skip: every step runs, and only the "wait for the user's reply" moments are replaced by the decision rules in the cited steps.

Input

Same defaults as fable-validate: issue URL, #<N> / <N> / owner/repo#N, or nothing (defaults to the latest open issue in the current repo).

Steps

Follow fable-validate-loop steps 1 through 4 with the changes below, then run this skill's step 5 in place of fable-validate-loop's steps 5 and 6:

Step 1 (fable-validate): also keep the verdict block and the validation report in the scratchpad; step 4 passes them to the planner. It produces the standard verdict block:

**#<N>: Update issue description? <Yes|No>**  ·  Complexity: <score>/100 — Capability <k> (Risk <r>, Uncertainty <u> — <driver>); Volume <v> (Scope <s>, Coupling <c>, Verification <x>) · fableplan: <yes|no>  ·  Scope: <OK | too large — split/umbrella/narrow>

Step 2 (scope gate): the same four STOP conditions apply; the cost here is a wasted or wrong plan rather than a wrong PR:

Condition Action
Scope: too large (split / umbrella / narrow flagged) STOP. Report the disposition and proposed parts — splitting is a human call.
Architecture marked ❌ Infeasible STOP. Report the infeasibility and the "Optimal direction" note.
A merged PR already implements the fix STOP. Report the PR and the close/repurpose recommendation.
An open PR is already addressing the issue STOP. Report the overlapping PR; supersede/join/wait is a human call.

Read the full file on GitHub · 55 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. 7d ago Changed · +4 tokens per session 3197386f6bba
  2. 11d ago First seen · 55 lines · 58 tokens per session scan A fe783e665a94

Subscribe to this mod's changes

fable-validate-fableplan is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,540 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 2026-08-30.