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 sanky369/vibe-building-skills --skill fable-like-implementationgit clone --depth 1 https://github.com/sanky369/vibe-building-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/sanky369/vibe-building-skills/fable-like-implementation)<a href="https://agentmods.dev/skills/sanky369/vibe-building-skills/fable-like-implementation"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/fable-like-implementation/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/sanky369/vibe-building-skills/fable-like-implementation"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/fable-like-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00153 | $0.03035 |
| Opus 5 | $0.00077 | $0.01517 |
| Sonnet 5 | $0.00031 | $0.00607 |
| Haiku 4.5 | $0.00015 | $0.00303 |
Grade A, and why
fable-like-implementation 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 11d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable-Like Implementation Planning
Transform an initial request into an implementation-ready engineering plan. No production code is written by this skill. The output is a plan package another agent (or human) can execute with minimal clarification.
When this skill applies — and when it must not
Model gate (check first): this skill runs ONLY when the current session model is Opus 4.8 (claude-opus-4-8). Check your own model identity from the system prompt/environment. If you are Claude Fable 5 or any other model, do not execute this skill — handle the request normally without it. Do not switch models or claim to be Opus 4.8 to satisfy the gate; the gate reflects the user's routing preference, not a capability requirement to work around.
If the model gate passes, apply when ANY of these are true:
- Change spans 3+ files or introduces a new module/subsystem
- API contract, database schema, or public interface changes
- New dependency, framework, or external service integration
- Migration, large refactor, or anything with rollback concerns
- The request is ambiguous enough that two engineers would build different things
Skip (answer directly, no plan) when ALL of these are true:
- Single-file, low-risk, obvious change
- No new dependencies, no contract changes
- A competent engineer would just do it without a design doc
If skipped, say so in one line ("This is trivial — implementing directly") so the choice is visible.
Hard rules (apply throughout)
- Never start implementation until the plan is complete AND the user explicitly approves. The plan is the deliverable.
- Read
CLAUDE.md(repo root and any nested ones) before anything else. Its conventions override this skill's defaults. - Reuse over rebuild — every proposed new component must state why an existing one can't serve.
- Assumptions are first-class — never silently assume. Every assumption gets logged with confidence (High/Med/Low) and the question that would resolve it.
- Cite sources for load-bearing technical decisions (official docs URL + the specific claim relied on).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 158 lines · 153 tokens per session scan A a0b3ee5b2580
fable-like-implementation is a skill published in the GitHub repository sanky369/vibe-building-skills (30 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 3,035 once invoked, about $0.0008 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.
Other skills, from other repositories
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
env-manager
An environment-variable manager for project settings stored outside the code, often in .env files. It checks variable definitions and usage while keeping secret values out of reports and terminal output.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.