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.
npx skills add richkuo/rk-skills --skill fable-validate-loopgit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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.
[](https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-loop)<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-loop"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-loop/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.
<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-validate-loop"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-validate-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00219 | $0.02401 |
| Opus 5.5 | $0.00088 | $0.00960 |
| Sonnet 5.5 | $0.00044 | $0.00480 |
| Haiku 4.5 | $0.00022 | $0.00240 |
Grade A, and why
fable-validate-loop 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-validate-loop
Chain fable-validate → (conditional) update issue → (conditional) fableplan → work-on-issue-loop into one unattended run. Parse each skill's output and proceed where the interactive skill would wait for the user, except at the STOP rows below.
Do not skip or reorder the chain. Validation gates planning, and the plan gates implementation. The only sanctioned skip is the step-4 score gate. Every other step of each skill still runs.
Input
Same as fable-validate: issue URL, #<N> / <N> / owner/repo#N, or nothing (the issue named, validated, planned, or filed in this session; with none, stop and ask). Never pick an issue from a list.
Optional targetBranch ({ issue, targetBranch } or a prose "target branch ") passes unchanged to every validate, plan, and build step; work-on-issue step 1 ("Target") owns its validation.
Steps
1. Run fable-validate
Invoke fable-validate (Skill tool) for the issue and let it run fully. It emits 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>) · plan: <yes|no> · Scope: <OK | too large — split/umbrella/narrow>
A Close issue? verdict or a Validation blocked line takes the block's place (validate-issue step 8); step 2 stops on both. Parse it yourself. Record the resolved issue as the full reference owner/repo#N: the repository from the user's reference (URL or owner/repo#N), else gh repo view --json nameWithOwner -q .nameWithOwner in the current checkout. Every later step and every skill this chain invokes gets that full reference and targets exactly this issue. A bare number resolves against the current checkout, so no handoff passes one.
2. Scope and decision gate
First check the verdict's Scope field, Architecture section, and Concerns (for an already-addressing PR), and the state fable-validate and fable-dispatch ended in. Rows (a) to (c) are Fable validation only: a chain that validates with plain validate-issue does not apply them.
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.
- 14d ago Changed · +1 lines · +9 tokens per session 1a6d15707e72
- 15d ago Changed · -4 tokens per session 913988ed24a0
- 16d ago Changed 9e86b6f92c0f
- 18d ago Changed · -1 lines 38d237521741
- 21d ago Changed · -1 lines · +162 tokens per session ec10370534e7
- 22d ago Changed · +11 lines 0fc9d9d11ba3
- 23d ago Changed f282b01a91ae
- 27d ago Changed · +1 lines 0aae4bdcbe86
- 1mo ago Changed · -10 lines d9a80db3b252
- 1mo ago First seen · 85 lines · 52 tokens per session scan A 399a3f8cecbd
fable-validate-loop is a skill published in the GitHub repository richkuo/rk-skills (50 stars, last pushed yesterday), licensed MIT. It adds 219 tokens to every session and 2,401 once invoked, about $0.0009 per session on Opus 5.5. 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.
Other skills, from other repositories
triage
A process for reviewing issues and outside pull requests through category and status labels. An issue is a recorded problem or request, while a pull request is a proposed code change for review.
criticism-self-criticism
A structured review method for examining completed work, criticism, and repeated mistakes. It focuses on specific evidence, causes, effects, and practical improvements.
refactor
Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract…
walkthrough
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR…
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
understand
Review and understand freshly AI-generated code. Scans the current repo's uncommitted/branch changes and builds a Claude-style light-themed two-column webpage — left is the project folder tree of changed files, right is the selected file's syntax-highlighted diff (additions/deletions clearly distinguished from…