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 humanerd-drew/opencode-drewgent --skill reference-gap-assessmentgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/reference-gap-assessment)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/reference-gap-assessment"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/reference-gap-assessment.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 5.1 | $0.00000 | $0.01454 |
| Opus 5 | $0.00000 | $0.00727 |
| Sonnet 5 | $0.00000 | $0.00291 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
reference-gap-assessment 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 3d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
title: reference-gap-assessment name: reference-gap-assessment description: Evaluate the user's system/expertise against an external article, framework, book, or paper. Extracts the reference's conceptual framework, maps each dimension to the user's context, and delivers an evidence-based scored assessment with actionable gaps. type: skill domain: assessment tags: [skill, assessment, framework, gap-analysis, evaluation] created: 2026-06-11 updated: 2026-06-11 links:
- "[[@identity/persona/writing-style-guide]]"
- "[[skills/harsh-critic]]"
- "[[skills/software-development/codebase-structure-audit]]"
- "[[@identity/brain/rules]]"---
reference-gap-assessment
When the user shares an external article, paper, framework, or book and asks "how am I doing against this?" or "evaluate my system against this", use this skill.
Trigger Conditions
- User shares a URL or reference and asks for assessment ("어떻게 보니?", "어느 정도 반영되고 있나?")
- User describes a framework and asks to be evaluated against it
- Session goal involves comparing user's work against an external standard
Core Principle
Extract → Map → Score → Gap.
The user values honest partial scores, not blanket "looks good." Every dimension gets a concrete score with evidence. Every gap gets a specific recommendation. The output format follows the user's preference for evidence-based assessment with a clear "what's good / what's missing / what's next" structure.
User Preference Embedding
- "정직한 부분-점수 답변" 선호: Score each dimension separately (e.g. 7/10), never give a vague overall "looks good." Every score must have supporting evidence.
- 옵션 + "내 추천" framing: After presenting gaps, offer 1-2 concrete improvement ideas with "내 추천" label.
- 근거 우선: Claims must be backed by specific examples from the user's system (code, files, previous decisions, memory records). "I think" without evidence is weak.
- 최종 요약: End with a compact table (dimension | score | evidence) for quick scanability.
What ships with it
1 file 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.
- 3d ago First seen · 152 lines · 0 tokens per session scan A d932abd2958e
reference-gap-assessment is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,454 tokens. 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…