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/azank1/cdv/copilot-instructionsgit clone --depth 1 https://github.com/azank1/cdvWhat 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 | $0.00353 | $0.00353 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
cdv 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 2d 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.
What it actually says
CDV — Agent Instructions
CDV is an MCP server for prompt quality, refinement loops, and Conservative Dual-Verify agent-loop control. See README.md for architecture, tools, and examples.
Required on every message
Always call cdv_intercept with the user's exact prompt before responding. Do not skip this even for simple requests.
cdv_intercept(prompt="<user's exact message>")
Act on the returned route: elicit → clarify first | decompose → plan first | refine → proceed directly.
For non-trivial tasks use cdv_run_pipeline as the entry point.
For multi-step iterative work, use cdv_loop_start → cdv_loop_step(step_output=...) → cdv_loop_end. Submit step artifacts; do not self-grade. The verdict includes cdv_mode (full = independent critic consulted; channel_a_only = deterministic checks only).
Memory & recovery (v0.8)
Recall before planning. For tasks similar to past work, call cdv_recall("<goal>") before planning. cdv_loop_start also returns similar_episodes automatically — read them. If cdv_intercept returns recall_available: true, recall first. cdv_loop_end records the outcome to episodic memory automatically.
Resume after an IDE reload. Call cdv_run_status. If it shows an active run, call cdv_loop_resume (optionally with session_id) before starting a new loop, so the in-progress loop continues instead of restarting cold.
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.
- 2d ago First seen · 30 lines · 353 tokens per session scan A 01b55af0854e
cdv copilot-instructions.md is an instructions file published in the GitHub repository azank1/cdv (4 stars, last pushed 28d ago), licensed MIT. It adds 353 tokens to every session, about $0.0018 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
Claude-Skills GEMINI.md
Gemini CLI instructions for borghei/Claude-Skills, covering gemini.md, project overview, how to use skills with gemini cli, 1. browse available skills and 2. activate a skill.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
agentic-playwright skill-creator.instructions.md
Instructions for idavidov13/agentic-playwright, covering skill creator, communicating with the user, creating a skill, capture intent and interview and research.
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
domain-experts CLAUDE.md
Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.
agent-skills AGENTS.md
Instructions for helderberto/agent-skills, covering agents.md, repository overview, project structure, integration model and opencode integration.