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.
npx skills add ai-driven-dev/framework --skill 01-usagegit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/01-usage)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/01-usage"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/01-usage/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/ai-driven-dev/framework/01-usage"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/01-usage.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 | $0.00069 | $0.00451 |
| Opus 5.5 | $0.00028 | $0.00180 |
| Sonnet 5.5 | $0.00014 | $0.00090 |
| Haiku 4.5 | $0.00007 | $0.00045 |
Grade A, and why
01-usage 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 today.
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.
What it actually says
Usage
flowchart TD
question([question]) --> probe{"aidd answers telemetry?"}
probe -->|"no"| absent([say it is missing, answer nothing])
probe -->|"yes"| frame
frame -->|"no axis fits"| refuse([say what the report cannot split by])
frame --> answer
answer -->|"refused or unknown version"| stop([say so])
answer --> told([figures, with what is unknown])
Actions
Run the flow above. Read only the next action file.
| Action | Does |
|---|---|
| frame | map the question to a period, one axis and the filters it fixes, and name the command |
| answer | run it, read the JSON, and state the figures with what is unknown |
Transversal rules
- Probe first. Run
aidd telemetry --helpbefore any action. Whenaiddis not found, or the command exits non-zero, stop and say plainly thataiddis missing or too old to report, name@ai-driven-dev/clias what to install or update, and state that no figure is available. Never answer from memory, from the session, or from anything but the report. - Every figure comes from
aidd telemetry report --json. Never add, subtract, average, convert or estimate a number, and never turn tokens into money: the report holds counts only. - Keep input, output, cache read and cache write apart. A total is the report's own
total, not a sum made here. - An unknown is unknown, never zero. Say so whenever the report shows one.
- Read only. Nothing here declares a task, turns measurement on, or changes any file.
What ships with it
3 files 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.
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.
- today First seen · 36 lines · 69 tokens per session scan A 8df78039b022
01-usage is a skill published in the GitHub repository ai-driven-dev/framework (519 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 451 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.