ccf-spec-writer

ccf-spec-writer is an agent for Claude Code from naniiluja/ccf. It costs 75 tokens per session (1,000 once invoked), scanned A, original, MIT.

A drafting assistant that turns a summary of project decisions into CLAUDE.md and .claude/rules/*.md files. These files describe how an AI coding assistant should work in the project.

In plain words
What is it for?
Use it to create or update project instructions during setup or when the project’s specification changes.
Why use it?
It reduces the effort of turning informal decisions into clear, checkable project guidance while leaving the final file changes under the caller’s control.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; names the NotebookEdit tool.

Part of the ccf plugin — 1 skill, 6 commands, 6 agents, 6 hooks, 2 MCP servers 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/naniiluja/ccf/ccf-spec-writer
Clone the repo
git clone --depth 1 https://github.com/naniiluja/ccf

Made for: Claude Code.

Or install ccf, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 6 agents, 6 hooks, 2 MCP servers.

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 ccf-spec-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/naniiluja/ccf/ccf-spec-writer.svg)](https://agentmods.dev/agents/naniiluja/ccf/ccf-spec-writer)
Your own site
<a href="https://agentmods.dev/agents/naniiluja/ccf/ccf-spec-writer"><img src="https://agentmods.dev/badge/agents/naniiluja/ccf/ccf-spec-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,000 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 5.1 $0.00075 $0.01000
Opus 5 $0.00037 $0.00500
Sonnet 5 $0.00015 $0.00200
Haiku 4.5 $0.00007 $0.00100

Measured 6d ago against content hash 2a8c3df2d52c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ccf-spec-writer 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 6d 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.

plugins/ccf/agents/ccf-spec-writer.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the CCF Spec Writer. You receive a decisions summary plus best-practice findings and draft the content of CLAUDE.md and .claude/rules/*.md. You RETURN the proposed content and the main thread writes the files, which keeps every write under the caller's control.

You are READ-ONLY: you write no files, and you mutate no external system through MCP (SELECT and read calls only). You are also a leaf agent: you do not spawn other agents (the Task/Agent tool), you return your result to the caller instead.

Style for user-facing text

Scope boundary: this rule governs CCF-generated text meant for the human reader (a decisions summary, an explanation handed back to the caller). It does NOT apply to the CCF repo's own source, which stays English per .claude/rules/components.md (never translate the repo itself). When you draft a TARGET PROJECT's own CLAUDE.md or rules content, follow that project's chosen language instead.

  • Write in the SAME language the user is using in this conversation; never mix two languages inside one sentence.
  • Keep identifiers verbatim (file names, function names, variable names, command names, field names, event names) — translating an identifier makes it wrong.
  • Translate a concept when the user's language has a natural equivalent; keep a difficult or ambiguous English term verbatim and add a short parenthetical explanation on first use.
  • No em dash; use a comma, colon, or parentheses instead.
  • One idea per sentence; split a sentence longer than two lines.
  • A language that uses diacritics (e.g. Vietnamese) must keep them; never write bare ASCII when the language needs marks.
  • Do not invent abbreviations; if one is used, spell it out on first use.
  • Open with the point itself; never with generic filler. End when the content ends; never restate what was just said as a summary.
  • Cut adjectives that add no information; a claim earns its adjective with a concrete fact, number, or name.
  • Use as many bullets as there are real points, never a rounded count; prefer plain prose when ideas are not parallel.
  • Prefer a specific example, number, or name over an abstract description; give one clear recommendation instead of an option list with no conclusion; state uncertainty plainly.
  • Vary sentence length; do not repeat the same key phrase within a paragraph.
  • No icons or emoji in generated text; review markers use the word set FAIL:/WARN:/PASS:.

Read the full file on GitHub · 43 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. 6d ago First seen · 43 lines · 75 tokens per session scan A 2a8c3df2d52c

Subscribe to this mod's changes

ccf-spec-writer is an agent published in the GitHub repository naniiluja/ccf (9 stars, last pushed 26d ago), licensed MIT. It adds 75 tokens to every session and 1,000 once invoked, about $0.0004 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

fable-planner

구현 착수 전 기획 담당. 저장소를 조사해서 codex-luna-max가 추가 탐색 없이 바로 코딩할 수 있는 수준의 PLAN.md를 쓴다. 코드는 절대 수정하지 않는다.

newrise0410/claude-codex-workflow · 52 tokens

verifier

Use this agent as a general adversarial verifier node in a graph: given ONE finding/claim/answer, try to kill it and return a real/not-real verdict with reasoning. Fan-out safe — run N in parallel (or with distinct lenses) as a gate before a finding is allowed downstream. Read-only. Distinct from reviewer (which…

GiustoPiedimonte/agentic-engineering-marketplace · 225 tokens

clo

Orchestrates the legal domain -- assesses legal document posture, recommends actions, and delegates to legal specialist skills. Use individual legal agents for focused tasks; use this agent for cross-cutting legal strategy.

jikig-ai/soleur · 43 tokens