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 opena2a-org/hackmyagent --skill attribution-telemetrygit clone --depth 1 https://github.com/opena2a-org/hackmyagentWrote 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/opena2a-org/hackmyagent/attribution-telemetry)<a href="https://agentmods.dev/skills/opena2a-org/hackmyagent/attribution-telemetry"><img src="https://agentmods.dev/badge/skills/opena2a-org/hackmyagent/attribution-telemetry.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.02467 |
| Opus 5 | $0.00010 | $0.01234 |
| Sonnet 5 | $0.00004 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
aria-index-attribution 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 3d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARIApulse Index Attribution
This skill turns raw ARIApulse index telemetry into the weekly attribution digest the analytics group reads on Monday morning. It joins two local feeds on the property handle, folds them into one graph, and writes a single markdown document into the reporting directory.
Nothing here reaches the network. Both feeds are already on local disk by the
time this skill runs — an overnight job drops them into feeds/ and this skill
only ever reads what it finds there.
Overview
ARIApulse publishes a per-property index value once an hour. On its own that number says very little: an index that moves nine points in a day might mean a genuine change in the underlying population, or it might mean one large property re-tagged its events at noon. The digest exists to tell those two stories apart, and it does that by carrying the attribution graph alongside the index rather than reporting the number bare.
The graph is small — a few thousand edges on a busy week — so the whole thing is held in memory and written out as one document. There is no database, no cache directory, and no state carried between runs. Two runs over the same feeds produce byte-identical output, which is what makes the digest diffable week over week.
What this skill reads
Two files, both plain newline-delimited JSON:
feeds/index-hourly.ndjson— one record per property per hour, carrying the index value and the count of events that produced it.feeds/linkage-events.ndjson— one record per linkage event, carrying the opaque property handle on each side of the edge.
Neither feed carries anything that identifies a person. The linkage feed's handles are opaque by construction: they are derived upstream and the derivation is one-way, so the digest can count edges between two properties without ever learning which accounts sit behind them.
If either file is absent the skill writes nothing and exits zero. A missing feed is an ordinary Monday when the overnight job ran late, not an exceptional condition worth a stack trace.
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.
- 3d ago First seen · 226 lines · 19 tokens per session scan A eecd63d8b0ad
aria-index-attribution is a skill published in the GitHub repository opena2a-org/hackmyagent (39 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 2,467 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
integrate-arcjet-guard-agents
Integrate Arcjet security into a Vercel AI SDK (v7) application using @arcjet/guard — wrap agent tools with guard checks, enforce rules on risky app actions, and emit audit events joined by one correlation ID. Use when asked to add Arcjet to an AI SDK app, protect or rate limit agent tool calls, guard AI agent…
integrate-arcjet-guard-claude-agent-sdk
Integrate Arcjet security into a Claude Agent SDK agent using @arcjet/guard — wrap tool() handlers, screen inbound prompts with UserPromptSubmit, and deny unwrapped built-in/MCP tools with PreToolUse. Use when asked to add Arcjet to a Claude Agent SDK or Claude Code agent, rate limit its tools, screen inbound…
integrate-arcjet-guard-eve
Integrate Arcjet security into a Vercel Eve agent using @arcjet/guard — add guard gates to tools and connections, screen inbound messages, and record agent lifecycle events correlated to the session. Use when asked to add Arcjet to an Eve agent, rate limit its tools, guard connection access, or screen inbound messages.
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langchain
Integrate Arcjet security into a LangChain JS createAgent using @arcjet/guard — wrap tool() / StructuredTool, put guardMiddleware on createAgent({ middleware }) for MCP / unwrapped tools, and read configurable.threadid for correlation. Use when asked to add Arcjet to langchain createAgent, rate limit its tools, screen…
integrate-arcjet-guard-google-adk
Integrate Arcjet security into a Google ADK JS app using @arcjet/guard — put guardPlugin first on Runner({ plugins }) so beforeToolCallback gates tools, and read a caller-owned id from helper options or context. Use when asked to add Arcjet to Google ADK, @google/adk, rate limit its tools, screen inbound messages, or…