fable-verify

A read-only completion check for existing coding work, such as a diff, branch, pull request, or claimed finished change.

In plain words
What is it for?
Use it to report which conditions are met or unmet, with evidence, without editing or committing changes.
Why use it?
It reduces false confidence by establishing the requirements, inspecting the actual work, and reproducing tests or flows instead of trusting earlier claims.

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/ayborg43/fable-mode/fable-verify
Any agent
npx skills add ayborg43/fable-mode --skill fable-verify
Clone the repo
git clone --depth 1 https://github.com/ayborg43/fable-mode

Made for: Claude Code, Codex.

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 655 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 $0.00133 $0.00655
Opus 5 $0.00067 $0.00328
Sonnet 5 $0.00027 $0.00131
Haiku 4.5 $0.00013 $0.00065

Measured 2d ago against content hash 3728cbf2c7d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable-verify 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 2d 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.

companions/fable-verify/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fable Verify

A standalone run of fable-mode's completion gate: verify that existing work actually does what it claims, without having done the work yourself. You are the fresh eyes — do not adopt the implementer's framing, and do not trust any result you did not reproduce in this session.

This skill changes nothing. Read code, run tests, exercise flows — but no edits, no fixes, no commits. If the user wants findings fixed, that's the next task, not this one.

Procedure

  1. Establish the spec. Find the checkable conditions the work is measured against, in this order: a SPEC/state file on disk (e.g. NOTES.fable.md), the PR or commit description, the user's statement of what was supposed to happen. If none yields checkable conditions, ask once — all questions in one message — then commit to the answer.
  2. Inventory the claim. Identify the diff, branch, or artifacts said to be done. git diff/git log the actual change — verify against what exists, not what was described.
  3. Run the verification yourself. Execute the tests, the harness, the build — whatever proves each condition. "The tests pass" in a report is a claim; the test run in your session is evidence.
  4. Exercise the real flow for anything user-facing: run the command, hit the endpoint, open the page. Tests alone miss wiring mistakes — code that exists but is never called.
  5. Read the diff as a skeptical reviewer: constraint violations, out-of-scope changes, silent scope creep, half-finished edges the happy path hides.
  6. When a fable-verifier agent type is available and the work is large, delegate the adversarial pass to it and consolidate its findings with your own.

Report

Lead with the verdict: VERIFIED (every condition met with evidence), NOT VERIFIED (any condition unmet or unprovable), or VERIFIED WITH FINDINGS. Then:

  • The condition checklist — each item met or not met, with the command output that proves it. A condition you cannot evidence is not met, however plausible.
  • Findings, most severe first, each with file, line, and the concrete failure scenario.
  • What you checked and found clean, in a sentence or two — so a clean verdict is distinguishable from a shallow look.

Read the full file on GitHub · 30 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. 2d ago First seen · 30 lines · 133 tokens per session scan A 3728cbf2c7d0

Subscribe to this mod's changes

fable-verify is a skill published in the GitHub repository ayborg43/fable-mode (2 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 655 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

edge-to-edge

Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.

android/skills · 67 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

referral-program

When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…

Eronred/aso-skills · 159 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens