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 daypunk/LockedIn --skill lockedin-render-ideasgit clone --depth 1 https://github.com/daypunk/LockedInWrote 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/daypunk/lockedin/lockedin-render-ideas)<a href="https://agentmods.dev/skills/daypunk/lockedin/lockedin-render-ideas"><img src="https://agentmods.dev/badge/skills/daypunk/lockedin/lockedin-render-ideas/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/daypunk/lockedin/lockedin-render-ideas"><img src="https://agentmods.dev/badge/skills/daypunk/lockedin/lockedin-render-ideas.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 | $0.00092 | $0.00656 |
| Opus 5 | $0.00046 | $0.00328 |
| Sonnet 5 | $0.00018 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
lockedin-render-ideas 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
render-ideas
Status: v1.2 (calibrated). Research-based calibration complete.
RUBRIC.md ships with five cross-source-validated dimensions. A
banned_phrases.json (27 entries, each backed by 2+ sources) and
research-notes.md (7 cited sources) ship alongside the prompts.
Pass/fail fixture corpus under tests/fixtures/ideas/.
Use this when
- The user asks "what should I work on next" or "ideas for side projects" or names a constraint and asks for proposals.
- The user wants to surface novel combinations of their existing skills and domains.
- The user asks for career-move pitches grounded in their actual experience.
Do NOT use when
- The user wants a resume or cover letter →
render-resume-en/render-jaso. - The user wants an interview answer →
render-interview. - The vault is sparse. Seed first via
/lockedin initor ingestion.
Two-turn pattern
Writer turn surfaces 3 to 5 ideas. Reviewer turn re-loads RUBRIC.md
fresh and scores the set on five dimensions.
Output shape
3 to 5 ideas, each one paragraph long, with a one-sentence pitch
followed by two to three sentences of rationale that cite vault
entities. Slug citations ([[type/slug]]) are resolved to natural
language by the orchestrator before the user sees the artifact.
Files in this directory
SKILL.md (this file)
research-notes.md 7 cited sources, cross-source analysis summary
banned_phrases.json 27 entries, severity-tagged, each backed by 2+ URLs
prompt-writer.md writer-turn instruction
prompt-reviewer.md reviewer-turn instruction (re-loads RUBRIC.md fresh)
RUBRIC.md 5-dimension scoring contract + score bands
Calibration status
v1.2 calibrated. The rubric dimensions (feasibility, novelty,
evidence_ground, scope_match, motivation_alignment) are grounded in
cross-source public research from Atlassian, Inc., FasterCapital,
Proposify, Built In, fundsforNGOs, and arXiv. The banned_phrases.json
contains 27 entries across five categories (buzzword_opener,
vague_enthusiasm, hedging_language, unsubstantiated_claim,
comparison_shortcut), each backed by 2+ independent sources. Pass and
fail fixture corpus is at tests/fixtures/ideas/{pass,fail}/
(3 pass, 3 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.
- 9d ago First seen · 71 lines · 92 tokens per session scan A bbec809d431b
lockedin-render-ideas 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 656 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
resume
Generate a tailored resume AND cover letter for a job description via the native four-role Resume Team, score both against ATS and HR rubrics, create DOCX files, and update the tracker. Use when the user pastes a job description and wants a complete application package (resume plus cover letter) with dual scoring and…
writing-coach
Human-voice writing coach that rewrites resumes and cover letters for brevity, burstiness, plain language, and authentic impact, and blocks AI-sounding prose. Use when the user wants to improve writing quality, fix robotic or generic AI-sounding text, cut fluff, strengthen bullets and summaries, or pass the…
cover-letter
Create a compelling one-page, human-voice cover letter for a job description and generate the final DOCX. Use when the user wants a cover letter only (no resume), pastes a JD and asks for a letter, or needs a letter to accompany an already-tailored resume. Runs the mandatory humanvoiceaudit before producing the DOCX.
find-jobs
Search live job boards for roles that match the master resume, then score and rank them by ATS and HR fit. Use when the user wants to discover or find jobs, search openings by title or location, wants remote roles, or asks which live listings best match their background. Uses the discoverjobs MCP tool and never…
job-fit
Run the deterministic, digest-bound candidate-fit gate that scores the configured master resume against an exact job description before any resume tailoring. Use when the user wants a GO/NO-GO fit check on a JD, asks "should I apply", or before starting resume work, to confirm score >= 70 with zero hard knockouts.…
setup
One-time setup for Resume Builder — Python dependencies, config.json, cloud or local scoring, and optional LLM features. Use once right after installing, or when the user reports missing dependencies, a missing or incomplete config, wants to switch between cloud and local scoring, or wants to enable AI-augmented…