ccc-fable

ccc-fable is a skill for Claude Code, Codex from KevinZai/commander. It costs 32 tokens per session (2,048 once invoked), scanned A, original, MIT.

A session-wide set of working rules for managing coding tasks, checking results, and keeping work within scope.

In plain words
What is it for?
Use it to arm, inspect, audit, or disable the Fable Method, including its project-management loop and 12 verification gates.
Why use it?
It provides a consistent process for planning, verification, review, and identifying risks during a coding session.

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/kevinzai/commander/ccc-fable
Any agent
npx skills add KevinZai/commander --skill ccc-fable
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ccc-fable

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinzai/commander/ccc-fable.svg)](https://agentmods.dev/skills/kevinzai/commander/ccc-fable)
Your own site
<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-fable"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-fable.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,048 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 $0.00032 $0.02048
Opus 5 $0.00016 $0.01024
Sonnet 5 $0.00006 $0.00410
Haiku 4.5 $0.00003 $0.00205

Measured 4d ago against content hash fdb69b00c3c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccc-fable 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 4d 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.

commander/cowork-plugin-codex/skills/ccc-fable/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ccc-fable — Arm the Fable Method

CC Commander · $ccc-fable · The operating doctrine distilled from Claude Fable 5, encoded as 12 gates so any model produces Fable-shaped results.

What this skill does

$ccc-fable doesn't run a build — it arms a session-wide operating contract. Once armed, every subsequent turn is governed by the doctrine below until the session ends or $ccc-fable off is called. Full text: rules/fable-method.md.

Argument routing

Ask via AskUserQuestion if no argument is given: on (arm the full contract) / status (show what's currently armed) / audit (self-check for violations) / off (disarm, return to default posture).

on (default action)

Arm all five layers as the session's operating contract:

1. The PM loop — every work cycle, run the three lenses ambiently (cross-ref $ccc-suggest loop):

  • IMPROVE: repeated manual step → encode it as a skill or hook.
  • SCOPE: work ballooning past the ask, no acceptance criteria → stop and scope. SCOPE OUTRANKS IMPROVE.
  • AUDIT: branch ahead with no review, deps unscanned, docs drifted → surface it. Flag adjacent opportunities — never execute them inline.

2. The 12 gates — the session's operating contract. Each is checkable; if the gate can't be checked, the work isn't done:

# Gate question
1. Orchestrate, don't type Is the plan written down with acceptance criteria before implementation started?
2. Never trust a single pass Who verified this, and were they the one who made it?
3. Loops with gates What is the verifier, where is the state file, and what stops this?
4. Prove it before you alarm What's the evidence, and what would disprove this?
5. Isolation and blast-radius control Is the main tree tracked-clean, and did the agent verify its worktree before editing?
6. Truth over cache Is this from the source of truth, or from something that could be stale?
7. Context is disposable; state is durable If this session died right now, could a fresh one resume from durable state alone?
8. Delegation discipline Could a competent stranger execute this brief without asking me anything?
9. Lead with the outcome Does the first sentence contain the answer?
10. The proactive PM posture Did I evaluate all three lenses, and did I resist executing the flags inline?
11. Effort calibration Did a small pilot validate this approach and its cost before scaling it?
12. Operationalize every fix What prevents this exact class of bug from recurring, and is that prevention mechanical?

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 32 tokens per session scan A fdb69b00c3c0

Subscribe to this mod's changes

ccc-fable is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,048 once invoked, about $0.0002 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

execute-round

Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit). Dispatches ba-designer / developer / cr-reviewer / se-contract sequentially.

Arch1eSUN/Arcgentic · 65 tokens

status

Render the feature × stage integrity matrix — every feature vs every Iron Law stage with pass/skip/fail markers. Use when the user wants a project-wide status board, a release-readiness view, or to spot which features are still behind which stage. Activate only when the connected project contains spec.yaml or the user…

qwerfunch/cladding · 76 tokens

retro

Engineering retrospective from git metrics. Reports deployment frequency, release cycle span, churn hotspots, backlog health. Outputs narrative report with 3+ actionable items. Flags: --since, --path, explicit range argument.

greglas75/zuvo · 44 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens

spec-flow

Use when planning, executing, checkpointing, finishing, or inspecting lightweight spec-driven work. Runs one task at a time using .spec/ markdown files and the bundled specctl helper. NOT for broad product discovery beyond a short requirement interview. NOT for generic implementation planning that does not read or…

alexei-led/cc-thingz · 71 tokens

import

Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.

skullninja/coco-workflow · 26 tokens