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 telemetrygit 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/telemetry)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/telemetry"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/telemetry/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/telemetry"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/telemetry.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 | $0.00146 | $0.01019 |
| Opus 5.5 | $0.00058 | $0.00408 |
| Sonnet 5.5 | $0.00029 | $0.00204 |
| Haiku 4.5 | $0.00015 | $0.00102 |
Grade A, and why
telemetry 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telemetry
telemetry answers two questions about work already done: what did it cost, and whose was it.
It never causes the work and never installs anything on a project's behalf. Everything it reads
already exists on disk because a tool wrote it, so the whole context is a set of readers, a set
of attribution rules, and one sink.
Where the sink and the run journal live, what the report renders, and what each tool declares
about being measured are in aidd_docs/memory/telemetry.md. Read that for the facts; this page
says where new code goes and what it must not do.
What goes in
| Concept | Location |
|---|---|
| A rendered answer's shape | domain/cost-report.ts, domain/cost-report-envelope.ts |
| How a figure is tied to something | domain/step-attribution.ts, domain/task-attribution.ts, domain/flow-attribution.ts |
| Reading one tool's own file format | domain/formats/ (one module per tool's transcript or export) |
| A stored record and what happens to it over time | domain/telemetry-sink-record.ts, domain/telemetry-sink-retention.ts |
| Who a session was for, and how strongly that is known | domain/person-resolution.ts, domain/ports/person-identity-reader.ts, domain/ports/person-identity-store.ts |
| Something telemetry needs from outside itself | domain/ports/ — declared here, satisfied at the composition root |
| The concrete reader behind one of those ports | infrastructure/ |
One question the aidd telemetry command asks |
application/ |
How
- A tool declares, telemetry reads. What a route was measured to supply, and where a tool's
transcripts live, are declared in
kernel/measurement.tsand filled in per tool undercontexts/tools/domain/profiles/<tool>/. Every field there is required on purpose: a default would be a capability nobody measured, quietly asserted for a tool nobody looked at. Never add a branch on a tool id inside this context. - What telemetry needs from another context, it declares as its own port.
installed-plugins-reader.tsandignore-entries.tsare the pattern: telemetry states the question,runtime/wiring/telemetry.tshands it an answer, and no context reaches into telemetry in return. - A figure with no established denomination is not an amount. A zero whose denomination was never established, a credit and a premium request are each their own thing; conflating them is how a report lies without ever being wrong about a number.
- An interval derived from the run journal is this CLI's inference, not the tool's statement.
Keep the two distinguishable in whatever you add —
toolStatedStepexists for exactly that. - Follow the use-case and port/adapter rules in
.claude/rules/00-architecture/.
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.
- 1mo ago First seen · 69 lines · 146 tokens per session scan A dccdaa7a33de
telemetry is a skill published in the GitHub repository ai-driven-dev/framework (518 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 1,019 once invoked, about $0.0006 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 2026-09-09.
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.
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.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.