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 DataSift-Ty-Personal/SiftStack --skill candidate-intakegit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWrote 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/candidate-intake)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/candidate-intake"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/candidate-intake/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/candidate-intake"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/candidate-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00183 | $0.02278 |
| Opus 5.5 | $0.00073 | $0.00911 |
| Sonnet 5.5 | $0.00037 | $0.00456 |
| Haiku 4.5 | $0.00018 | $0.00228 |
Grade A, and why
candidate-intake 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 2mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Candidate Intake
Turn applicants who arrive through many different channels into one running, scored master Google Sheet, then help the user pick who to contact and send the outreach. This is a recruiting funnel in a box: it does not matter whether someone applied on Indeed, emailed a resume, commented on a Facebook job post, or sent a Messenger DM. They all land in the same sheet, scored the same way, so the user has a single ranked view of every candidate.
Indeed -+
Gmail -+
FB post-+--> normalize --> score --> dedupe --> ONE master Google Sheet
FB DM -+ |
paste -+ v
review ranked list --> approved outreach
The guiding idea: organize and score everyone first, then let the user decide who gets outreach. Never message people before the user has seen the ranked list and chosen. That review gate is the whole point, so respect it.
Prerequisites
This skill works almost entirely through the browser, so a community member can use it with zero API keys or developer setup.
- Claude in Chrome extension connected. Gmail, Facebook, Indeed, and Google Sheets are all read and written through Chrome. If it is not connected, ask the user to connect it before proceeding.
- A Google account with the applicant channels logged in in that Chrome profile (Gmail, and Facebook if they use it).
- A master Google Sheet. Setup helps the user create one, or point at an existing sheet.
- A config file,
.candidate-intake-config.json, saved in the working folder. It holds the role definition, scoring rubric, sheet URL, and outreach templates so every run and the daily sweep behave consistently.
Step 0: Setup (run once, or when the role changes)
Before the first intake, check the working folder for
.candidate-intake-config.json.
- If it is missing, run setup: read
references/setup-and-config.mdand follow it. Setup collects the role and company, the must-have and nice-to-have criteria, the screener questions and their ideal answers, the scoring weights, the sender's first name, and the outreach templates. It then creates (or adopts) the master Google Sheet and writes the header row. Save the result to.candidate-intake-config.jsonusingassets/config.template.jsonas the shape. - If it exists, load it and continue. If the user says the role or criteria changed, re-run the relevant part of setup and save.
What ships with it
11 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.
- assets/config.template.json 2.5 KB
- references/intake-facebook.md 2.4 KB
- references/intake-gmail.md 2.1 KB
- references/intake-indeed.md 2.2 KB
- references/intake-manual.md 2.3 KB
- references/outreach.md 2.7 KB
- references/scoring-rubric.md 2.9 KB
- references/setup-and-config.md 3.3 KB
- references/sheet-schema.md 2.4 KB
- scripts/prepare_rows.py 4.5 KB runs code
- scripts/score_candidates.py 5.5 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.
- 2mo ago First seen · 189 lines · 183 tokens per session scan A 36befbd12db4
candidate-intake is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 183 tokens to every session and 2,278 once invoked, about $0.0007 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.
candidate-intake compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| candidate-intakeDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 183 | 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 |