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 ErikaAX08/erikas-skills --skill verify-before-implementgit clone --depth 1 https://github.com/ErikaAX08/erikas-skillsWrote 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/erikaax08/erikas-skills/verify-before-implement)<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/verify-before-implement"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/verify-before-implement/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/erikaax08/erikas-skills/verify-before-implement"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/verify-before-implement.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 | $0.00056 | $0.08749 |
| Opus 5.5 | $0.00022 | $0.03500 |
| Sonnet 5.5 | $0.00011 | $0.01750 |
| Haiku 4.5 | $0.00006 | $0.00875 |
Grade A, and why
verify-before-implement 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 — 968 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VERIFY-BEFORE-IMPLEMENT.md — Reality-First Implementation Skill
Purpose: this is the operational rulebook an AI agent (or a human) follows before and while writing code, to prevent the most common AI failure mode in software engineering — inventing parameters, endpoints, fields, types, status values, config keys, or library APIs that sound plausible but don't exist in the actual codebase, contract, or dependency being used.
This file is self-contained by design. It doesn't assume the codebase has any particular language, framework, or stack — the verification method below applies the same way to a Python Django service, a Go microservice, a React frontend, or a bash script. Where a project has its own stricter standards (an API-contract skill, an architecture skill, a commit-message skill), those win on their specific topic — this file is the general-purpose verification discipline underneath all of them, not a replacement for any of them.
0. How to use this file
- Before writing any code, identify what you're about to touch — an API contract, a database model, a type/interface, a config value, a third-party library call, a CLI flag, a UI component — and pick the matching checklist in §6. Every category has the same shape: find the actual definition, copy it verbatim, verify against it, don't proceed on a guess.
- While reading, follow the source-of-truth hierarchy in §3 and the pre-implementation sequence in §4. If you hit something you can't verify, don't push through it — follow the decision tree in §5.
- While implementing, keep running notes per §7 (verified facts, explicit assumptions, gaps found) — this is what makes §9's conflict-resolution and §12's escalation possible instead of silent guessing.
- Before calling anything "done", run the checklist in §11 and the self-review questions under it. §10 is a list of failure modes already known to happen — check the change doesn't repeat one of them.
- If something is genuinely ambiguous even after following §3–§6, stop and ask (§5 step 4, §12) — don't resolve the ambiguity by picking the answer that lets you keep typing.
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.
- yesterday Changed c47efa29f513
- 3d ago Changed · +40 lines 0967beaafd31
- 1mo ago First seen · 928 lines · 56 tokens per session scan A d26264a54b54
verify-before-implement is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 8,749 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…