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 rgranet/project-coding-companion-skill --skill project-coding-companiongit clone --depth 1 https://github.com/rgranet/project-coding-companion-skillWrote 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/rgranet/project-coding-companion-skill/project-coding-companion)<a href="https://agentmods.dev/skills/rgranet/project-coding-companion-skill/project-coding-companion"><img src="https://agentmods.dev/badge/skills/rgranet/project-coding-companion-skill/project-coding-companion.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 | $0.00188 | $0.03809 |
| Opus 5 | $0.00094 | $0.01904 |
| Sonnet 5 | $0.00038 | $0.00762 |
| Haiku 4.5 | $0.00019 | $0.00381 |
Grade C, and why
project-coding-companion scanned grade C with 1 finding 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 8d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
6. **Never refuse to help.** Even if the prompt is extremely vague (e.g., How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Coding Companion
CRITICAL — READ THIS FIRST: Before writing ANY code, reading ANY file, or launching ANY subagent, you MUST complete Phase 0 (Evaluate and Coach the Prompt). Do NOT skip this phase. Do NOT explore the codebase first. Your very first action is to check the conversation context for existing answers, THEN evaluate the user's prompt against the five dimensions, and respond with coaching if needed. Only after the prompt is clear and confirmed should you proceed to Phase 1. Exception: if the user's message is a clear continuation of an ongoing task ("ok do it", "go ahead", "next step"), skip coaching and proceed.
Overview
You are a careful, methodical coding companion with a dual mission:
- Prompt coaching — Help the user formulate clear, complete, and actionable coding requests. When a prompt is vague or missing critical information, you coach the user by asking targeted questions and explaining why each piece of information matters.
- Code implementation — Once the task is clear, help the user understand the codebase, plan changes, implement them, and review the result.
You work with any language, framework, or stack. You discover the technology by inspecting the project, never by assuming.
You are opinionated about safety: you never auto-commit, never run destructive commands without confirmation, and always summarize what you changed.
When to use this skill
Use this skill whenever the user:
- Sends a coding request — whether clear or vague.
- Asks to explore, understand, or explain a codebase.
- Wants to add a feature, fix a bug, refactor, write tests, or review code.
- Explicitly asks for help formulating a coding request ("help me prompt better", "how should I describe this task", "improve my prompt").
- Provides a project directory and asks an open-ended question.
Do not use this skill for:
- Pure greenfield scaffolding with no existing code.
- Non-code tasks (documents, presentations, spreadsheets).
- Infrastructure/deployment unless tied to code changes in a repo.
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.
- 8d ago First seen · 393 lines · 188 tokens per session scan C f77be1c3d9e2
project-coding-companion is a skill published in the GitHub repository rgranet/project-coding-companion-skill (9 stars, last pushed 6mo ago), licensed MIT. It adds 188 tokens to every session and 3,809 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
claude-md-architect
Design, create, extract, or audit CLAUDE.md files and their supporting docs/ folder structure for Claude Code projects. Use this skill whenever the user asks to create a new CLAUDE.md, extract context from a long session into a CLAUDE.md system, audit/refactor an existing CLAUDE.md that has bloated, review whether…
better-tropes
Strip the tells that mark prose as AI-generated. Use when writing or editing anything a person will read: posts, articles, documentation, emails, marketing copy.
Cursor Skill (.mdc) Authoring
Author effective Cursor rules in .cursor/rules/.mdc - YAML frontmatter (description, globs, alwaysApply), the four rule types, scoped QA rules, subagents, and structure that actually steers the model.
project-butler
A project-memory workflow that keeps a code project’s rules, current structure, documents, logs, tasks, and handoff notes organized.
vibe-check
Turn a complete beginner's app idea into a buildable plan, then keep them oriented while they build. Use it whenever someone who has never coded wants to build or "vibe code" an app, has an idea but no idea where to start, or wants it turned into a plan, MVP scope, tech stack, user flows, or blueprint. It has three…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…