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/mzored/init-deep/copilot-instructionsgit clone --depth 1 https://github.com/mzored/init-deepWhat 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 | $0.00426 | $0.00426 |
| Opus 5 | $0.00213 | $0.00213 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
init-deep 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
init-deep
Multi-platform AI documentation compiler. Python 3.11, no external deps.
Commands
python3 scripts/build_init_deep.py # Regenerate adapters
python3 scripts/check_init_deep.py # Validate sync
python3 -m src.init_deep.cli check # Validate registry-generated adapters
python3 -m src.init_deep.cli lint # Validate source schema
python3 -m src.init_deep.cli doctor # Check workspace health
python3 -m unittest discover -s tests -v # Run tests
Architecture
Two-layer design: a typed compiler pipeline and a legacy compatibility layer.
New pipeline: source/commands/init-deep/spec.toml + body.md are parsed into CommandSpec, lowered to CommandIR, and rendered by 9 built-in target plugins in src/init_deep/targets/.
Legacy: source/init-deep/canonical.md is the original single-file source. tools/init_deep/renderers.py generates platform-specific output. Legacy scripts delegate to the new pipeline.
Conventions
- Edit
spec.toml+body.md; keepsource/init-deep/canonical.mdbyte-identical for legacy compatibility - Never hand-edit generated
skills/oradapters/; rebuild them - CI enforces sync: build then
git diff --exit-code - Pure stdlib Python, no external dependencies
- Each platform is a
TargetPluginclass withplan(),render(),validate()methods - Tests read actual files, no mocks (273+ tests)
Pitfalls
- Gemini adapter is TOML, not Markdown
- Copilot instructions and prompts are budget-sensitive; do not assume the prompt contains the full workflow
managed_paths()glob list must be updated when adding adapters--skip-*flags are CLI-only, not inspec.toml
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 · 41 lines · 426 tokens per session scan A 6798f524beb2
init-deep copilot-instructions.md is an instructions file published in the GitHub repository mzored/init-deep (6 stars, last pushed 2mo ago), licensed MIT. It adds 426 tokens to every session, about $0.0021 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
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
Skill_Seekers AGENTS.md
Instructions for yusufkaraaslan/Skill_Seekers, covering agents.md - skill seekers, project overview, key capabilities, setup and with dev tools (pytest, ruff, mypy, coverage).
ungate AGENTS.md
Instructions for orchidfiles/ungate, covering ungate — architecture and project structure, purpose, monorepo (pnpm workspace), data flow and apps/api — proxy server.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
pbi-context CLAUDE.md
Instructions for Osc2405/pbi-context, covering estado actual (actualizado 2026-07-15), actualización 2026-08-03 — rename pbi-docs → pbi-context, 0. contexto del proyecto (no re-investigar, ya validado), 1. feature obligatoria: soporte .pbip / tmdl and por qué es obligatoria (contexto de mercado, no opinable).
pitchdocs copilot-instructions.md
Instructions for littlebearapps/pitchdocs, covering pitchdocs — copilot instructions, project structure, conventions, sync points and protected files.