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 agentmods add skills/oleg494/coding-kit/fable-judgenpx skills add oleg494/coding-kit --skill fable-judgegit clone --depth 1 https://github.com/oleg494/coding-kitWhat 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 | $0.00098 | $0.01268 |
| Opus 5 | $0.00049 | $0.00634 |
| Sonnet 5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
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.
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.
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).
- 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.
- Establish what actually changed.
git diffandgit 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. - 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.
- 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 saidline 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'sreferences/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 infable-method'sreferences/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 againstbrand.md, figures re-fetched, arithmetic recomputed.
- 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.
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.
- 2d ago First seen · 42 lines · 98 tokens per session scan A 7dfbc2fc7004
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 $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to fable-judge, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.
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.
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…
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…
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…
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…