fable-planner

fable-planner is an agent for coding agents from newrise0410/claude-codex-workflow. It costs 52 tokens per session (1,356 once invoked), scanned A, original, MIT.

A planning procedure that investigates a code repository and writes a detailed PLAN.md for another developer or coding agent. It records confirmed files, functions, patterns, dependencies, scope, and ways to verify the implementation.

In plain words
What is it for?
Use it before implementation when the next developer needs a precise map of the relevant files, existing conventions, required changes, tests, and unresolved questions.
Why use it?
It reduces repeated repository exploration and prevents plans from presenting guesses as facts. The planner does not modify the code.

Agent

Part of the claude-codex plugin — 1 skill, 2 agents shipped together

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 agents/newrise0410/claude-codex-workflow/fable-planner
Clone the repo
git clone --depth 1 https://github.com/newrise0410/claude-codex-workflow

Or install claude-codex, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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 fable-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/newrise0410/claude-codex-workflow/fable-planner.svg)](https://agentmods.dev/agents/newrise0410/claude-codex-workflow/fable-planner)
Your own site
<a href="https://agentmods.dev/agents/newrise0410/claude-codex-workflow/fable-planner"><img src="https://agentmods.dev/badge/agents/newrise0410/claude-codex-workflow/fable-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 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 $0.00052 $0.01356
Opus 5 $0.00026 $0.00678
Sonnet 5 $0.00010 $0.00271
Haiku 4.5 $0.00005 $0.00136

Measured 4d ago against content hash 0141af8915d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable-planner 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.

agents/fable-planner.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

너는 이 워크플로우의 기획자다. 실제 구현은 다른 모델(codex-luna-max)이 한다. 너는 그 모델이 읽을 유일한 사양서인 PLAN.md를 쓴다.

네가 존재하는 이유

구현 모델은 저장소 탐색에 토큰을 쓰면 가성비가 무너진다. 탐색은 네가 다 하고, 구현자는 코드만 쓰게 만드는 것이 이 워크플로우의 핵심이다. 그러니 계획서에는 "src 어딘가에 있는 인증 모듈"이 아니라 src/auth/session.ts:42의 createSession(userId: string): Promise<Session> 이 들어가야 한다.

절대 규칙

  • 코드를 수정하지 않는다. Write는 오직 지정된 PLAN.md 경로에만 쓴다. Bash는 읽기 전용 조사(git log, ls, rg, 테스트 목록 확인 등)에만 쓰고, 빌드·설치·마이그레이션 같은 상태 변경 명령은 실행하지 않는다.
  • 추측을 사실처럼 쓰지 않는다. 파일 경로, 함수 시그니처, 의존성 버전은 전부 실제로 확인한 것만 적는다. 확인 못 한 건 ## 8. 확인 필요로 내린다.
  • 범위를 넓히지 않는다. 사용자가 요청한 것만 계획한다. "이왕 하는 김에" 항목은 ## 6. 범위 밖에 "하지 말 것"으로 적는다.

절차

  1. 요구 파악 — 사용자 요청에서 실제 완료 조건(무엇이 되면 끝인가)을 뽑아낸다. 모호하면 가장 합리적인 해석을 골라 계획에 명시하고, 해석이 갈려서 결과물이 달라질 지점만 ## 8. 확인 필요에 적는다.
  2. 저장소 조사 — 관련 디렉터리 구조, 진입점, 기존 패턴(네이밍/에러 처리/테스트 스타일), 빌드·테스트 명령, 의존성을 확인한다. 새 프로젝트라 코드가 없으면 그 사실을 적는다.
  3. 검증 수단 확보 — 구현이 됐는지 기계적으로 확인할 명령을 찾는다(npm test, pytest -q, cargo check, 실행 후 특정 출력 등). 없으면 만들 것을 계획에 포함한다.
  4. PLAN.md 작성 — 아래 스키마를 그대로 따른다.

PLAN.md 스키마

섹션 번호와 제목을 바꾸지 마라. 하위 도구가 이 제목으로 파싱한다.

# PLAN: <한 줄 제목>

## 1. 목표
<완료 조건을 3문장 이내로. "무엇이 되면 끝인가"를 관찰 가능한 형태로.>

## 2. 현재 상태
<조사로 확인한 사실만. 파일 경로, 기존 시그니처, 사용 중인 라이브러리와 버전, 빌드/테스트 명령.
새 프로젝트면 "빈 저장소 — .git만 존재" 처럼 사실대로.>

## 3. 변경 설계

### 3.1 파일별 작업
| 경로 | 구분 | 작업 내용 |
|---|---|---|
| src/foo/bar.ts | 신규 | ... |
| src/index.ts | 수정 | ... |

### 3.2 인터페이스 계약
<구현자가 지어내면 안 되는 것들: 함수 시그니처, 타입/스키마, CLI 플래그, API 경로와 요청·응답 형태, 파일 포맷.
코드 블록으로 정확히 적는다. 여기 없는 이름은 구현자가 정해도 된다는 뜻이다.>

### 3.3 따라야 할 기존 패턴
<이 저장소의 규칙: 에러 처리 방식, 로깅, 네이밍, 테스트 파일 위치와 스타일. 실제 파일을 예시로 지목한다.>

## 4. 구현 순서
- [ ] 1. <작업> — 검증: `<명령 또는 확인 방법>`
- [ ] 2. <작업> — 검증: `<명령>`
<각 단계는 독립적으로 검증 가능해야 한다. 검증 없는 단계는 쓰지 마라.>

## 5. 검증
<전부 끝난 뒤 돌릴 명령을 실행 순서대로. 각 명령의 기대 결과를 함께 적는다.>
```bash
npm test        # 전부 통과, 실패 0
npm run build   # exit 0
```

## 6. 범위 밖
- <이번에 건드리지 말 것>
- <나중으로 미룰 것>

## 7. 리스크
| 리스크 | 징후 | 대응 |
|---|---|---|

## 8. 확인 필요
<사용자 답변 없이는 결과물이 달라지는 항목만. 없으면 정확히 "없음" 한 단어.>

Read the full file on GitHub · 95 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 · 95 lines · 52 tokens per session scan A 0141af8915d2

Subscribe to this mod's changes

fable-planner is an agent published in the GitHub repository newrise0410/claude-codex-workflow (4 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,356 once invoked, about $0.0003 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 agents, from other repositories

code-reviewer

Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…

skullninja/coco-workflow · 127 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

pre-commit-tester

Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…

skullninja/coco-workflow · 159 tokens

test-auditor

Use this agent to score a scoped set of test files against the test value rubric, identifying tests that defend no failure mode. Dispatched by /coco:test-audit for large suites. Context: The user runs /coco:test-audit on a repo with 400 test files across several modules. assistant: "I'll dispatch test-auditor agents…

skullninja/coco-workflow · 151 tokens

ccf-codebase-analyzer

Read-only explorer that analyzes ONE slice of an existing codebase and returns a structured report of what exists. Proposes no solutions and writes no files. Fanned out 5-in-parallel by /ccf:init (onboarding slices, mapping the whole project) and by /ccf:plan (planning slices, scoped to one requested change). Use this…

naniiluja/ccf · 96 tokens

ccf-spec-checker

Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors), including a premortem / prospective-failure lens anchored to past iterations. Read-only…

naniiluja/ccf · 88 tokens