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 00-initgit 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/00-init)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/00-init"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/00-init/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/00-init"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/00-init.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 | $0.00099 | $0.00768 |
| Opus 5 | $0.00049 | $0.00384 |
| Sonnet 5 | $0.00020 | $0.00154 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
00-init 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init
flowchart LR
ask([project]) --> check --> enable --> verify
check -.->|"already on"| verify
verify --> recording([recording])
A second, independent choice belongs to the person rather than the project: whether their own records carry an identifier at all.
flowchart LR
ask2([this person]) --> identify
identify -.->|"already chose"| status1([relayed, unchanged])
identify -->|"opted in"| withdraw([forget: withdraw naming])
withdraw -.->|"never opted in"| status2([relayed, unchanged])
A third, independent ask reaches the same action, and needs neither of the two above: removing what this tool measured, wholly, on this machine.
flowchart LR
ask3([asks to be forgotten]) --> shown([forget: shown what would go, and what history keeps])
shown -->|"confirms"| removed([removed, in counts shown])
shown -.->|"declines"| status3([nothing removed])
Actions
Run the flow above. Read only the next action file.
| Action | Does |
|---|---|
| check | confirm the CLI and read the current switch |
| enable | ask, then turn measurement on |
| verify | prove a session is actually being recorded |
| identify | ask this person, then attach their own identifier, and offer to link another identifier as the same one |
| forget | withdraw naming, or remove everything this tool measured — two different asks, one action |
Transversal rules
- Measuring someone's project is theirs to allow. Ask before turning it on, always.
- Naming a person is theirs alone to allow, separately from the project switch above — never assumed from the project being measured, never asked on someone else's behalf.
- Run only
aidd telemetry on --yes,aidd telemetry off,aidd telemetry identity's own verbs, andaidd telemetry forget's own verbs (preview first,--yesonly after this person has seen it and confirmed). Never a script, and never a command belonging to another skill. aidd telemetry identitynever reads.aidd/config.jsonorAIDD_USER_CONFIG_DIR— both are settings a repository or a CI job can set, and this choice is not theirs to make. It reads and writes only this machine's own user profile.- Removing what was measured is irreversible, and reaches further than one project: this machine's stored records span every project ever measured on it, not only the one being discussed. Never presented as reversible, and never presented as scoped to one project when it is not.
- What history keeps is relayed exactly as
aidd telemetry forgetstates it — a journal already committed as certainly held, one merely staged but never committed as not yet held, one not tracked at all as possibly held — and is never presented as removable. No command in this skill rewrites git history. - The
aiddcommand cannot be found: say so and change nothing.
What ships with it
5 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.
- yesterday First seen · 58 lines · 99 tokens per session scan A 528cf1d00eea
00-init is a skill published in the GitHub repository ai-driven-dev/framework (460 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 768 once invoked, about $0.0005 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 2026-09-09.
Other skills, from other repositories
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…