Borrowing it
Nothing to install: this file belongs to saajunaid/caddis-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saajunaid/caddis-plugin/main/.github/instructions/advisory-mode.instructions.mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/advisory-mode)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/advisory-mode"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/advisory-mode/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/instructions/saajunaid/caddis-plugin/advisory-mode"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/advisory-mode.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 | $0.01618 | $0.01618 |
| Opus 5.5 | $0.00647 | $0.00647 |
| Sonnet 5.5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
caddis-plugin advisory-mode.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 1mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisory Mode Boundary
When GitHub Copilot is used in an advisory or planning conversation (not operating as a named agent), these boundaries are absolute and non-negotiable.
Activation Gate (Critical)
Use this boundary only when the user is explicitly operating the junai pipeline/orchestrator flow or pipeline-state based routing.
If the user is in a normal coding/planning chat and did not request pipeline orchestration, do not inject @Orchestrator routing requirements.
What advisory chat must NEVER do
- Edit production files, run terminal commands, or make code changes — those belong to a specialist agent in the project
- Exception: documentation-only planning artifacts may be created or updated as defined in the Documentation Write Exception below
- Compose pipeline stage handoff prompts — any prompt driven by
pipeline-state.jsonphase numbers is@Orchestrator's sole responsibility - Route directly to a pipeline agent by constructing the full phase brief, even when the next step seems obvious
What advisory chat is ALLOWED to do
- Read, explain, and reason about the codebase and pipeline state
- Diagnose a bug or symptom raised by the user in this conversation and produce a Diagnostic Brief for the appropriate specialist agent
- Create or update documentation-only planning artifacts when explicitly requested by the user, including:
.github/plans/*.md.github/handoffs/*.md- roadmap documents
- strategy notes
- implementation plans
- diagnostic briefs
Constraints for documentation writes
These writes are allowed only when all of the following are true:
- The artifact is non-executable documentation (
.md,.txt, or similar) - It does not modify production code, tests, build scripts, or runtime configuration
- It does not modify
.github/pipeline-state.json - It does not perform pipeline routing, gate satisfaction, or specialist-agent execution
- The write is limited to persisting planning or diagnostic context already discussed in the current conversation
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.
- 1mo ago First seen · 125 lines · 1,618 tokens per session scan A 26b5e09ef687
caddis-plugin advisory-mode.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 1,618 tokens to every session, about $0.0065 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.