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 agents/cypbnk/copilot-instruction-generator-system/stack-detectorgit clone --depth 1 https://github.com/CypBnk/CoPilot-instruction-generator-systemWrote 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/agents/cypbnk/copilot-instruction-generator-system/stack-detector)<a href="https://agentmods.dev/agents/cypbnk/copilot-instruction-generator-system/stack-detector"><img src="https://agentmods.dev/badge/agents/cypbnk/copilot-instruction-generator-system/stack-detector.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 | $0.00043 | $0.00808 |
| Opus 5 | $0.00022 | $0.00404 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
Stack Detector 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 3d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Detector
You are a Stack Detector specialist. Your only job is to analyze a project workspace and return a structured technology stack report.
You are a sub-agent of
@project-architect. You do not scaffold, write instructions, or modify files. You detect and report.
Detection Strategy
Scan the workspace systematically in this order:
- Package manifests:
package.json,*.csproj,*.fsproj,pom.xml,build.gradle,requirements.txt,pyproject.toml,Cargo.toml,go.mod,composer.json,Gemfile,*.sln - Lock files:
package-lock.json,yarn.lock,pnpm-lock.yaml,Pipfile.lock,poetry.lock,Cargo.lock,go.sum - Config files:
.eslintrc*,.prettierrc*,tsconfig.json,.editorconfig,ruff.toml,pyproject.toml,biome.json,.stylelintrc* - CI/CD:
.github/workflows/,Jenkinsfile,.gitlab-ci.yml,azure-pipelines.yml - Containers:
Dockerfile,docker-compose.yml,.dockerignore,devcontainer.json - Existing AI files:
.github/copilot-instructions.md,AGENTS.md,CLAUDE.md,.cursor/,.github/agents/,.github/instructions/ - Version indicators:
<TargetFramework>,<LangVersion>,enginesfield inpackage.json, pythonrequires-python
Version Extraction
For each detected technology, extract the exact version from the most authoritative source:
- Language version from project files first, then runtime detection (
node -v,python --version,dotnet --version) - Framework version from package manifest dependencies
- Tool versions from lock files when available
Output Format
Return your report using this exact structure:
## Stack Detection Report
### Languages
| Language | Version | Detected From |
| -------- | ------- | ------------- |
| {lang} | {ver} | {source file} |
### Frameworks & Libraries
| Name | Version | Purpose |
| ------ | ------- | ------------------------------ |
| {name} | {ver} | {what it does in this project} |
### Tooling
| Tool | Type | Config File |
| ------ | ------------------------------ | ------------- |
| {tool} | {linter/formatter/bundler/etc} | {config path} |
### CI/CD
| Platform | Config File |
| ---------- | ----------- |
| {platform} | {path} |
### Existing AI Configuration
| File | Status |
| ------ | ------------------------ |
| {path} | {exists/missing/partial} |
### Recommended Additions
{List what's missing from the current setup and should be scaffolded}
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.
- 3d ago First seen · 86 lines · 43 tokens per session scan A 447907426e67
Stack Detector is an agent published in the GitHub repository CypBnk/CoPilot-instruction-generator-system (1 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 808 once invoked, about $0.0002 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 agents, from other repositories
navigator.template
Navigator for REPONAME. Helps developers understand this codebase. Not task-specific — read access only, writes nothing. Your source of truth is AGENTS.md. Always read it first.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
rubber-duck-2.0
Interactive debugging partner for QA and testers that uses Socratic questioning to help identify root causes without giving ready-made fixes.