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 instructions/kunalsuri/ai-fication-kit/copilot-instructionsgit clone --depth 1 https://github.com/kunalsuri/ai-fication-kitWrote 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/instructions/kunalsuri/ai-fication-kit/copilot-instructions)<a href="https://agentmods.dev/instructions/kunalsuri/ai-fication-kit/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kunalsuri/ai-fication-kit/copilot-instructions.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 | $0.00582 | $0.00582 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
ai-fication-kit copilot-instructions.md 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 4d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo-wide instructions for GitHub Copilot
This repo's coding rules live in AGENTS.md (repo root) — read it in full before
making changes. It points to the ai/ knowledge layer: start at ai/INDEX.md,
then ai/guide/MODULE_MAP.md to find code by area before opening files.
Hard rules from AGENTS.md apply to every request in this workspace: respect
ai/guide/MODULE_MAP.md Stability (frozen/? = do not edit), keep diffs
surgical, match license headers, and never flip an [inferred] tag in ai/ to
[verified] yourself — that is a human signature. Every unit of work ends with a
row appended to ai/lab/WORKLOG.md, even work done outside the prompt files
below.
Slash commands available in Copilot Chat
This kit's workflows are available as prompt files under .github/prompts/ —
type / in chat to see them:
/cold-start— bootstrap theai/guidemaps and diagrams (draft-only,[inferred])/add-feature— spec first, then implement using the knowledge layer/fix-bug— reproduce first, failing regression test, root cause, surgical fix/review-change— fresh-context review of a finished change against its spec/check-drift— run the mechanical verify + drift checks/create-feature-catalog— mine the code for a feature → files catalog/perform-feature-add-simulation— dry-run a feature add without writing code/post-cold-start-verification— deep audit of the draftedai/docs/review-agent-config— structural check ofCLAUDE.md/AGENTS.md/verify-ai-readiness— score this repo's AI-readiness maturity
Custom chat modes under .github/chatmodes/ mirror the kit's subagents
(repo-explorer, feature-builder, test-runner) — switch to them from the
chat mode picker for read-only exploration, surgical implementation, or test
verification respectively.
Agent Skills
VS Code discovers Agent Skills from .claude/skills/ and .agents/skills/ in
this repo automatically — the add-feature skill (spec → locate → gate →
implement → verify → review & record) and the fix-bug skill (reproduce →
failing test → locate → gate → root cause → fix → verify → review & record)
apply to Copilot too; nothing Copilot-specific needed here.
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.
- 4d ago First seen · 43 lines · 582 tokens per session scan A cd2b94d46257
ai-fication-kit copilot-instructions.md is an instructions file published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 582 tokens to every session, about $0.0029 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 2026-08-31.
Other instructions, from other repositories
Koshi AGENTS.md
Instructions for jsharma1105/Koshi, covering koshi sub-agent personas, personas, prerequisites, python (pip install koshi) and .net tool (dotnet tool install).
cerebro-inevita GEMINI.md
Instructions for gabrielzucco/cerebro-inevita: Leia CLAUDE.md por inteiro: ele é o contrato canônico de operação deste cérebro. As skills portáveis vivem em .agents/skills/. Ative a skill adequada por linguagem natural; na primeira sessão, use comecar. Se as skills ainda não aparecerem no Gemini CLI, rode /skills…
ZipAI CLAUDE.md
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
tocket CLAUDE.md
Instructions for pedrocivita/tocket, covering claude.md - tocket, role, build & run, code style and architecture.
tocket GEMINI.md
Instructions for pedrocivita/tocket, covering gemini.md - tocket, role, protocol, payload format and memory bank.
claude-organizer CLAUDE.md
Instructions for ramakay/claude-organizer, a project described as: AI-powered file organization and context engineering that understands content, not patterns. Automatically sorts temporary scripts from permanent docs while preserving your workflow. Works seamlessly with Claude Code hooks. Protects README, LICENSE…