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 treasure-data/td-skills --skill identitygit clone --depth 1 https://github.com/treasure-data/td-skillsWrote 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/treasure-data/td-skills/identity)<a href="https://agentmods.dev/skills/treasure-data/td-skills/identity"><img src="https://agentmods.dev/badge/skills/treasure-data/td-skills/identity/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/treasure-data/td-skills/identity"><img src="https://agentmods.dev/badge/skills/treasure-data/td-skills/identity.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 | $0.00027 | $0.03053 |
| Opus 5.5 | $0.00011 | $0.01221 |
| Sonnet 5.5 | $0.00005 | $0.00611 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
identity 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
This skill is used when the user asks about identity stitching, id stitching, or wants to explore real time profiles. It involves querying two tables: id_changes (identity graph changes) and validation_failures (rejected key/value pairs). Both are updated by the application as events are processed.
Treasure Data's real time service includes creation and management of real time profiles. Profiles are updated based on a stream of event records that contain one or more "id stitching key" properties. The identity of a profile consists of both an internal Rid (real time Id) and one or more stitching keys. The system creates new profiles when the keys are all unique. It updates a profile when a new key is found that was not previously associated with other keys in the record. It can also stitch multiple profiles together when we find that keys in the record exist in two or more existing profiles. We combine the profiles together and the rid with the earliest date is the kept whilst the other profiles are merged and deleted.
Each profile can hold at most 200 associations (IDs + merged profiles). When an incoming event would push a profile past that limit, the lowest-priority associations are evicted to make room and a profile_ids_evicted row is written to id_changes recording what was removed.
Key/value pairs on incoming events that fail validation (wrong type, empty, not in config, case mismatch, failed regex, in invalid_texts) are excluded from stitching and logged to validation_failures. The event is still processed — validation never blocks live traffic.
Description
Requirements
In order to query the identity logs we must know the parent segment the customer is interested in. A customer may have a number of parent segments so we must ask them to provide the one they are interested in before making a query. A segment ID will be a numeric value like 411671.
The user must also have a correctly configured tdx-skill or the Treasure Data mcp server (@treasuredata/mcp-server) to enable the database lookup.
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 Changed · +104 lines · +15 tokens per session eebdf3fa7a44
- 2mo ago First seen · 104 lines · 12 tokens per session scan A 7e2b55627b80
identity is a skill published in the GitHub repository treasure-data/td-skills (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 27 tokens to every session and 3,053 once invoked, about $0.0001 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 2026-08-30.
identity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| identitytreasure-data/td-skills | Skill | 22 | 5d ago | Apache-2.0 | A | 27 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |