aiwork-protocol

aiwork-protocol is a skill for Claude Code from lttr/claude-marketplace. It costs 134 tokens per session (2,021 once invoked), scanned A, original, MIT.

A project folder protocol for saving AI work in dated folders, such as research, plans, specifications, reports, and decisions. The files remain in the project so later sessions can find the work.

In plain words
What is it for?
Use it when you need to triage a task, research a problem, write a specification or report, plan work, review code, or record decisions.
Why use it?
It prevents planning and research from becoming scattered across chats or files. It also helps keep related work together and makes overlapping folders easier to spot.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Status:** in-progress → `../2026-08-28_auth-layer/`.

Part of the aiwork plugin — 11 skills, 2 hooks shipped together

Good fit Use it when you need to triage a task, research a problem, write a specification or report, plan work, review code, or record decisions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/lttr/claude-marketplace
agentmods
npx agentmods add skills/lttr/claude-marketplace/aiwork-protocol

Made for: Claude Code.

Or install aiwork, the plugin that ships this one along with the rest of its 11 skills, 2 hooks.

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 aiwork-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/lttr/claude-marketplace/aiwork-protocol/github.svg)](https://agentmods.dev/skills/lttr/claude-marketplace/aiwork-protocol)
Your own site
<a href="https://agentmods.dev/skills/lttr/claude-marketplace/aiwork-protocol"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/aiwork-protocol/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aiwork-protocol

Your own site · 80×15
<a href="https://agentmods.dev/skills/lttr/claude-marketplace/aiwork-protocol"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/aiwork-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00134 $0.02021
Opus 5 $0.00067 $0.01010
Sonnet 5 $0.00027 $0.00404
Haiku 4.5 $0.00013 $0.00202

Measured 2d ago against content hash 930fd08d490f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aiwork-protocol 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.

plugins/aiwork/skills/aiwork-protocol/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.aiwork Folder Protocol

Repository-local folder for AI work artifacts, organized by feature or task. Artifacts structure thinking in-session and provide context for future sessions when referenced manually.

Folder layout

.aiwork/
  2026-01-27_auth-refactor/
    intent.md
    triage.md
    spec.md
  • Folder: {YYYY-MM-DD}_{slug}/, slug lowercase kebab-case, max 40 chars.
  • File: {type}.md. Numbering for multiples of same type:
    • plan.mdplan_2.mdplan_3.md — when one plan was expected, more followed.
    • plan_1.mdplan_2.mdplan_3.md — when multiple are expected from the start.
    • Don't mix schemes in one folder.
  • Multi-day: optionally prefix filenames with {YYYY-MM-DD}_.

Usually 1-2 artifacts per task. Pick types that fit.

Grouping and restructuring

One task = one folder. Drift signals:

  • Two folders with overlapping scope or near-identical slugs
  • Cross-folder references: / "Source plan: ../..." pointers
  • Folder that exists only because a ticket number arrived mid-task

On drift, propose consolidation: move artifacts into the canonical folder with a superseded_by: pointer, or merge under one date. Ask before moving files.

A pointer to an epic's areas.md is not drift — it's a legitimate parent link (see below). Drift is two folders for the same task.

Epics

A folder is dated when its work starts and holds a few hours' to a few days' work. A big idea doesn't fit: months can pass between framing it and finishing the last piece.

So split it. The epic folder is an index, not a task: spec.md (or nothing, when the framing is short) plus areas.md. Each area later becomes a normal task folder, dated when it actually starts.

.aiwork/
  2026-06-09_kurzy-platforma/     # epic, framed in June
    spec.md
    areas.md
  2026-08-28_auth-layer/          # area 02, started in August
    spec.md
    tickets/

The presence of areas.md is what marks a folder as an epic. Its area entries carry the roll-up:

Read the full file on GitHub · 182 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. 2d ago Changed · +6 lines · +6 tokens per session 930fd08d490f
  2. 5d ago Changed · +38 lines b8d781ec28d4
  3. 10d ago First seen · 138 lines · 128 tokens per session scan A 740064cf9a16

Subscribe to this mod's changes

aiwork-protocol is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 3d ago), licensed MIT. It adds 134 tokens to every session and 2,021 once invoked, about $0.0007 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

stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.

spencermarx/open-code-review · 18 tokens

hook-factory

Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.

alirezarezvani/claude-code-skill-factory · 36 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

development

An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.

fengshao1227/ccg-workflow · 41 tokens