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 agentmods add skills/dudarenok-maker/executive-application-helper/draft-gatenpx skills add dudarenok-maker/executive-application-helper --skill draft-gategit clone --depth 1 https://github.com/dudarenok-maker/executive-application-helperWrote 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/dudarenok-maker/executive-application-helper/draft-gate)<a href="https://agentmods.dev/skills/dudarenok-maker/executive-application-helper/draft-gate"><img src="https://agentmods.dev/badge/skills/dudarenok-maker/executive-application-helper/draft-gate.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 | $0.00203 | $0.04817 |
| Opus 5 | $0.00102 | $0.02409 |
| Sonnet 5 | $0.00041 | $0.00963 |
| Haiku 4.5 | $0.00020 | $0.00482 |
Grade A, and why
draft-gate 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 4d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Gate — consolidated Step-1-close verification skill
Setup note: This is a template skeleton. Replace
[Candidate Name],[Candidate First Name]and[Workspace Folder Path]. Buildreferences/sweep-checklist.mdfrom your own Section 7 register as it grows — that file is the only part of this gate that is candidate-specific.
One invocation, four checks, one report. This gate replaces the Step-1-close trio (length-check, watchouts-sweep, matrix-row-traceability) under the V6 structure: matrix rows now live at Matrix_Rows/<ID>.md, and length bands are keyed by channel, overlaying document types.
The gate exists because each check catches a real, recurring pre-delivery failure. Job boards truncate screening answers at their character limit silently. The watch-outs register carries the framework's hardest-earned overclaim discipline — every entry was added after a real overclaim was caught. And a draft that quietly swaps the matched row's tested body stack for ad-hoc evidence selection throws away the calibration the row encodes. The fourth is newer and the most brutal: a Selection Criteria Response that drops, merges or paraphrases one of the advertisement's criteria scores zero against that criterion no matter how good the prose is, because the panel scores the instrument, not the document.
MANDATORY — emit the verification checklist table
This gate is not run until its checklist is written down. Load references/checklist.md and emit that table in full in the report: one row per checklist item, each with an explicit verdict and the evidence that produced it. Never summarise. Never omit a row. Never write "all pass" without the table. If a row cannot be evidenced, its verdict is UNVERIFIED — and UNVERIFIED is treated as a FAIL for blocking purposes.
| # | Check | How verified (command / quote / count) | Result | Verdict |
|---|---|---|---|---|
| 0.3 | Em-dashes within cap AND not zero | Counted — in body text |
4 em-dashes, cap 6 | PASS |
| 1.2 | Screening answer Q2 within limit | awk … | wc -c after markdown strip |
1,043 chars (limit: 1,000 hard) | FAIL |
What ships with it
5 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.
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.
- 4d ago First seen · 205 lines · 203 tokens per session scan A 0d44c974bfc9
draft-gate is a skill published in the GitHub repository dudarenok-maker/executive-application-helper (2 stars, last pushed 16d ago), licensed MIT. It adds 203 tokens to every session and 4,817 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
file-organizer
Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files". Creates numbered PARA folders, renames poorly-named…
file-organizer
Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files", "declutter". Creates numbered PARA folders (0-Inbox…
qwen-vision
Use when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare videos", "analyze this image", "what's in this screenshot", or when the user provides a video/image file path and expects visual understanding.…
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…