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/daypunk/lockedin/lockedin-render-jasonpx skills add daypunk/LockedIn --skill lockedin-render-jasogit clone --depth 1 https://github.com/daypunk/LockedInWhat 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 | $0.00092 | $0.00805 |
| Opus 5 | $0.00046 | $0.00402 |
| Sonnet 5 | $0.00018 | $0.00161 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
lockedin-render-jaso 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 yesterday.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
render-jaso
Research-based calibration. RUBRIC.md ships with five dimensions and score bands. prompt-writer.md, prompt-reviewer.md, and banned_phrases.json (28 cross-source-confirmed entries) all ship.
Use this when
- User names a Korean company and asks to write a 자소서.
- User points at a 자소서 question (e.g., 지원동기 / 성장과정 / 성격의 장단점 / 입사 후 포부).
- User asks to "polish my 자소서" against the rubric.
Do NOT use when
- User wants an English resume → use
render-resume-en. - The vault is empty (no ontology nodes to quote) → seed first via
/lockedin initorlockedin init --fixture FILE.
Required design constraints (locked)
- 두괄식 — conclusion / 핵심 / 차별점 in the first paragraph; the rest of the answer scaffolds the lead.
- 구조화된 문맥 — within Korean 4-question convention (지원동기 / 성장과정 / 성격의 장단점 / 입사 후 포부 etc.), use STAR or PAR per paragraph.
- 두루뭉술한 표현 제거 — banned-phrase regex check runs before
the reviewer rubric pass. See
banned_phrases.json. - 초개인화된 경험 기반 — every claim quotes a concrete ontology
node by slug (e.g.,
[[role/lead-pm-fintech-2024]]). Vague generalities cost the 구체성 dimension. - 회사·직무 fit — query the ontology for nodes with edges to the target company / 직무 / industry; surface the top-3 most relevant before drafting.
Two-turn writer/reviewer pattern
Run as two separate Claude turns:
- Writer turn — produce the 자소서 draft. Quote ontology slugs. Apply banned-phrase filter to the draft.
- Reviewer turn — clear the writer context. Re-load
RUBRIC.mdfresh. Score on두괄식 / 구조화 / 구체성 / 표현 / 적합성(0–5 each). Emit JSON. If any dimension < 4 ORrevisions_required: true, return to the writer turn once with the review notes.
Same-turn self-evaluation inflates scores by ~1 point. Do not skip the separation.
Final checklist
- Banned-phrase regex pass ran (and was clean) before rubric.
- Reviewer turn was a separate Claude context with fresh RUBRIC.md load.
- Output JSON has all 5 dimensions ≥ 4 (or one revise cycle ran).
- Concrete ontology slugs are quoted in the rendered text.
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.
- yesterday First seen · 79 lines · 92 tokens per session scan A 9fffa5a82524
lockedin-render-jaso is a skill published in the GitHub repository daypunk/LockedIn (127 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 805 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
job-hunter
Job search assistant. Generate and polish resumes, write cover letters, track applications, prepare for interviews, and search for jobs. Use when the user asks about jobs, resume, cover letter, interview prep, or application tracking. Triggers on: "find me a job", "update my resume", "write a cover letter", "interview…
scrape
Finds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape.
upskill
Compares tracked job postings against the candidate profile to identify skill gaps and generate a prioritized learning plan with study resources. Triggers on: /upskill, upskill, skill gaps, what should I learn, learning plan.
freehire-search
Use this skill to search live software / tech / data / engineering job listings across many countries and markets (and remote) via the freehire.me aggregator's public API, or to look up a specific posting. It aggregates roles from 50 ATS platforms into one schema, so a single skill covers many markets — but its…
jobdanmark-search
Make sure to use this skill whenever the user mentions anything related to Danish job listings, job search in Denmark, finding work in Denmark, or job vacancies on Jobdanmark — even if they don't explicitly mention jobdanmark.dk. Also invoke this skill for questions about specific Danish job categories…
jobnet-search
Make sure to use this skill whenever the user mentions anything related to Danish job searching, job listings, job vacancies, employment opportunities in Denmark, or the Danish government job portal — even if they don't mention jobnet.dk explicitly. Also invoke this skill for questions about specific job titles…