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.
git clone --depth 1 https://github.com/lttr/claude-marketplacenpx agentmods add skills/lttr/claude-marketplace/aiwork-protocolWrote 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.
[](https://agentmods.dev/skills/lttr/claude-marketplace/aiwork-protocol)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.md→plan_2.md→plan_3.md— when one plan was expected, more followed.plan_1.md→plan_2.md→plan_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:
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.
- 2d ago Changed · +6 lines · +6 tokens per session 930fd08d490f
- 5d ago Changed · +38 lines b8d781ec28d4
- 10d ago First seen · 138 lines · 128 tokens per session scan A 740064cf9a16
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.
Other skills, from other repositories
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
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.
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.
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.
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…
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.