whip-docs

whip-docs is a skill for Claude Code, Codex from bang9/ai-tools. It costs 35 tokens per session (552 once invoked), scanned A, original, MIT.

A documentation-writing workflow that checks technical statements against the current code before writing or updating guides, READMEs, and API references.

In plain words
What is it for?
Use it to create or correct documentation for features, APIs, workflows, migrations, and upgrades.
Why use it?
It helps prevent documentation from describing behavior the software does not actually have.

Skill for Claude CodeCodex

Part of the whip plugin — 8 skills 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 skills/bang9/ai-tools/whip-docs
Any agent
npx skills add bang9/ai-tools --skill whip-docs
Clone the repo
git clone --depth 1 https://github.com/bang9/ai-tools

Made for: Claude Code, Codex.

Or install whip, the plugin that ships this one along with the rest of its 8 skills.

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 whip-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/bang9/ai-tools/whip-docs.svg)](https://agentmods.dev/skills/bang9/ai-tools/whip-docs)
Your own site
<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-docs"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00035 $0.00552
Opus 5 $0.00017 $0.00276
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 5d ago against content hash 872fe64e565d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

whip-docs 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 5d 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.

whip/skills-codex/whip-docs/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical writer who values accuracy over polish. You verify every claim against the current codebase before committing it to prose. You write for operators and engineers who need to execute — not for marketing audiences. You treat documentation as code: it must be correct, testable, and maintainable.

Non-negotiables

  • Draft concrete wording in the first turn. Do not stop at an audit, outline, or work plan when a documentation delta can be produced immediately.
  • Verify behavior claims against current code. If you cannot verify, call out the uncertainty explicitly rather than writing confidently.
  • Express mismatches between docs and code as documentation corrections, not code-review findings.
  • Structure material so another operator or agent can execute it without hidden context.

Workflow

Step 1: Scope

Identify what needs documenting:

  • New feature, API, or workflow
  • Existing docs that are stale or incomplete
  • Migration or upgrade guide

Read the relevant code and existing docs before writing.

Step 2: Verify

For each behavior or interface you plan to document:

  1. Read the source code that implements it
  2. Confirm the actual behavior matches what you intend to write
  3. If there is a mismatch, fix the docs to match the code (not the other way around)
  4. If behavior is ambiguous in code, note it as an open question

Step 3: Write

Follow these principles:

  • Concrete examples over abstract descriptions — show commands, code snippets, expected output
  • Explicit prerequisites — what must be installed, configured, or running
  • State transitions and failure handling — document what happens when things go wrong, not just the happy path
  • Technical correctness over marketing tone — no vague benefits, no AI-slop phrasing, no filler
  • Concise, high-signal prose — if a sentence adds no information, delete it
  • Sharp upgrade notes — when documenting changes, be explicit about what broke and how to migrate

Step 4: Self-check

Read the full file on GitHub · 54 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 54 lines · 35 tokens per session scan A 872fe64e565d

Subscribe to this mod's changes

whip-docs is a skill published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 552 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

backlog-technical-project-manager

Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization…

MrLesk/Backlog.md · 90 tokens

kanban-tui

Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the ktui command is not available, but uv is available utilize uvx kanban-tui…

Zaloog/kanban-tui · 80 tokens

verify-frontend-change

Verify a frontend change actually works in the GSD Task Manager app before trusting it. Drives the running app browser-first — seeds IndexedDB, busts the PWA service-worker cache, then observes real behavior plus console/network errors — and codifies regression-worthy behavior as a Playwright spec. Use whenever you've…

vscarpenter/gsd-task-manager · 0 tokens

verify-frontend-change

Verify a frontend change actually works in the GSD Task Manager app before trusting it. Drives the running app browser-first — seeds IndexedDB, busts the PWA service-worker cache, then observes real behavior plus console/network errors — and codifies regression-worthy behavior as a Playwright spec. Use whenever you've…

vscarpenter/gsd-task-manager · 0 tokens

branch-preflight

Sanity-check the working tree before starting plan execution or new branch work. Catches inherited damage that silently breaks verification later — merge conflict markers committed to tracked files, outstanding stash entries that may bleed into your work, uncommitted changes you may not realize you have. Runs in 1…

vscarpenter/gsd-task-manager · 105 tokens

reviewable-pr-slicing

Convert an approved technical plan into a sequence of small, reviewable PRs with clear phase boundaries, validation gates, and PR descriptions. Use for multi-step refactors, workflow changes, security-remediation tranches, documentation-plus-code rollouts, or any change that is too risky or noisy for one PR.

vscarpenter/gsd-task-manager · 68 tokens