Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStacknpx agentmods add skills/datasift-ty-personal/siftstack/account-blueprintWrote 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/datasift-ty-personal/siftstack/account-blueprint)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/account-blueprint"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/account-blueprint/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/datasift-ty-personal/siftstack/account-blueprint"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/account-blueprint.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 | $0.00125 | $0.01511 |
| Opus 5.5 | $0.00050 | $0.00604 |
| Sonnet 5.5 | $0.00025 | $0.00302 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
account-blueprint 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account Blueprint
Set up a DataSift account the way the reference account is set up, without clicking through 98 presets and 27 sequences by hand, and without trusting that a create "worked" because the server said 200.
Use when someone says "set my account up like the challenge account", "install the preset system", "clone the sequences", or "export my account structure".
What you get
One command creates, in dependency order, everything a working account needs:
| family | what lands |
|---|---|
| statuses | the custom lead statuses, with their colors |
| lists | the classification lists (Absentee Owners, Probate, Foreclosure, ...) |
| tags | only the tags the system uses (Priority 1, Courthouse Data, recently sold, ...) |
| custom fields | groups, fields and select options |
| task presets | task groups and the presets sequences create tasks from |
| presets | every preset folder and preset, filters translated to your account |
| sequences | folders and sequences, board columns and task presets re-linked |
| SiftMap | the auto-add presets, created with auto-add OFF |
Every object is read back after it is created and compared to what was sent. A preset whose saved filter differs from the one sent is a mismatch and the run exits 2. Anything that could not be reproduced is a named gap in the report, never a silent omission.
Requirements
- Python 3.10+ (stdlib only, nothing to install)
- Your own DataSift login. Either a JWT copied from the browser session, or your email and password (the script mints its own token)
- A blueprint file. The reference one is in
blueprints/
Run it
cd scripts
# 1. See what would happen. Nothing is written.
python clone_account.py --phase plan --blueprint ../blueprints/ty2_2026-09-10.json \
--target [email protected] --email [email protected] --password '...'
# 2. Create it. Still nothing is written without --commit.
python clone_account.py --phase apply --blueprint ../blueprints/ty2_2026-09-10.json \
--target [email protected] --email [email protected] --password '...' --commit
# 3. Check parity later, read-only.
python clone_account.py --phase verify --blueprint ../blueprints/ty2_2026-09-10.json \
--target [email protected] --jwt '<paste>'
What ships with it
13 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.
- blueprints/ty2_2026-09-10.json 256 KB
- references/blueprint-format.md 3.5 KB
- scripts/account_blueprint/__init__.py 1.1 KB runs code
- scripts/account_blueprint/apply.py 43 KB runs code
- scripts/account_blueprint/blueprint.py 7.8 KB runs code
- scripts/account_blueprint/cli.py 8.5 KB runs code
- scripts/account_blueprint/client.py 9.4 KB runs code
- scripts/account_blueprint/export.py 18 KB runs code
- scripts/account_blueprint/probe.py 4.8 KB runs code
- scripts/account_blueprint/report.py 4.1 KB runs code
- scripts/account_blueprint/staff_creds.py 2.3 KB runs code
- scripts/account_blueprint/translate.py 28 KB runs code
- scripts/clone_account.py 1.8 KB runs code
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 · 125 lines · 125 tokens per session scan A 7a48bc6da3cf
account-blueprint is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 125 tokens to every session and 1,511 once invoked, about $0.0005 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 2026-09-11.
account-blueprint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| account-blueprintDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 125 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |