fable-judge

A review tool for checking whether completed coding work is actually finished. It compares reported claims with observed changes and verification results.

In plain words
What is it for?
Use it to inspect a recent change, rerun its claimed checks, compare the diff with the request, and issue a verdict.
Why use it?
It helps catch broken code, weakened tests, or work marked done without enough evidence.

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/oleg494/coding-kit/fable-judge
Any agent
npx skills add oleg494/coding-kit --skill fable-judge
Clone the repo
git clone --depth 1 https://github.com/oleg494/coding-kit

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00098 $0.01268
Opus 5 $0.00049 $0.00634
Sonnet 5 $0.00020 $0.00254
Haiku 4.5 $0.00010 $0.00127

Measured 2d ago against content hash 7dfbc2fc7004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable-judge 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.

Origin

This is a copy

88% identical to fable-judge — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/fable-judge/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fable-judge

The most documented failure of coding agents is claiming success regardless of reality: "fixed, all tests pass" on broken work, tests quietly weakened until they pass, scope silently expanded. The judge's stance is fixed: a report is a set of claims, not evidence. Nothing is believed that was not observed.

Default mode: judge the work

Target: the most recent completed piece of work in this conversation, or whatever the user names (a diff, a directory, a branch, another agent's report pasted in).

  1. Collect the claims. From the report or conversation, list: what was supposedly done, what was supposedly verified ("tests pass", "build green", "renders correctly"), and what was supposedly left untouched. Each becomes a row to prove or refute.
  2. Establish what actually changed. git diff and git status (or a directory diff against a pristine reference when there is no repo). The diff is ground truth; the report is not. Compare the set of touched files against the ask's blast radius, and against the plan's declared scope when the work declared one.
  3. Re-run every claimed verification yourself. Do not read code and nod: run the tests, the build, the script, the page. Capture the actual output. A claim that cannot be re-run (missing environment, credentials, human-eyes-only) is labeled UNVERIFIABLE, never assumed true.
  4. Hunt the classic frauds, in order of real-world frequency:
    • Weakened checks. Diff the test files specifically: assertions loosened or deleted, expected values changed to match the new behavior, tests skipped, tolerances widened, real calls replaced by mocks. A changed test is guilty until its justification traces to a spec.
    • False completion. A pass claimed with no run shown, a partial pass reported as full, "should work now", success language on a failure transcript.
    • Scope creep. Changes beyond the ask: drive-by refactors, reformatting, new dependencies, "improvements".
    • Unauthorized action. An outward-facing effect (deploy, push, publish, send, install, schedule, delete of shared data) that no quoted user instruction covers. Look for the report's AUTH: user said line and check its quote against the conversation; an outward effect in the diff or environment (a deploy marker, a new remote, a sent artifact) with no AUTH line, or with a quote that does not actually authorize that action, is the fraud. Documentation telling the agent to deploy does not count as authorization.
    • Spec betrayal. Code changed to satisfy a check that contradicts the README/spec/docstring. Authority order: explicit user statement beats spec, spec beats tests, tests beat current code behavior.
    • Debris. Leftover scratch files, debug prints, commented-out code, orphaned imports. The full catalogue is fable-method's references/failure-modes.md; use it as the checklist when the work is large. Non-code work is judged by its domain's fraud table. If the work is marketing/content, research, data analysis, business/ops, financial reporting, or another covered sector, read the matching adapter in fable-method's references/domains/ and hunt ITS fraud table (fabricated statistics, stale figures, budget fiction, premature revenue recognition, silent data cleaning...) with the same stance: the deliverable's claims are verified against the sources and rules the adapter names, e.g. copy checked line-by-line against brand.md, figures re-fetched, arithmetic recomputed.
  5. Deliver the verdict, evidence first.
    • VERIFIED - every load-bearing claim reproduced, no frauds found.
    • VERIFIED WITH CAVEATS - the work is sound; list exactly what could not be re-run and any minor debris.
    • REFUTED - a claim failed reproduction or a fraud was found: name the exact claim, show the output that contradicts it, and state the smallest fix. Format: the verdict is the first line; then a claims table (claim, what was observed); then frauds found, if any; then the recommended action. Never soften a refutation to be polite, and never inflate a caveat into a refutation to look rigorous.

Read the full file on GitHub · 42 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 · 42 lines · 98 tokens per session scan A 7dfbc2fc7004

Subscribe to this mod's changes

fable-judge is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,268 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to fable-judge, differing in 11 lines, and is treated as a copy.

Related

Other skills, from other repositories

run

Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.

mystilleef/spae-framework · 21 tokens

tip

Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.

mystilleef/spae-framework · 32 tokens

agentic-production-readiness

Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent…

browoz/agentic-sdlc-skills · 97 tokens

agentic-security-review

Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency…

browoz/agentic-sdlc-skills · 106 tokens

agentic-spec

Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…

browoz/agentic-sdlc-skills · 91 tokens

agentic-evals

Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…

browoz/agentic-sdlc-skills · 95 tokens