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 commands/advenimus/conduit-desktop/devgit clone --depth 1 https://github.com/advenimus/conduit-desktopWhat 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 | $0.00000 | $0.00737 |
| Opus 5 | $0.00000 | $0.00368 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
dev 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 yesterday.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conduit Development Workflow
You are continuing development on Conduit, an AI-powered remote connection manager. Follow this workflow precisely.
Step 1: Read Documentation
Read these files to understand current state:
docs/PROGRESS.md- Check milestone status and task completiondocs/TECHNICAL_SPEC.md- Understand architecture (if needed)- Identify the current phase from PROGRESS.md (first phase with incomplete tasks)
- Read the corresponding phase doc:
docs/phases/PHASE_XX_*.md
Step 2: Assess Current State
Before writing any code:
- Check what exists: Use Glob/Grep to see what files/code already exist
- Identify the next incomplete task from the current phase
- Understand dependencies: What must exist before this task can be done?
Step 3: Implement
For each task:
- Implement the code following the phase documentation
- Follow existing patterns - check similar existing code first
- Keep changes focused - one task at a time
Step 4: Verify (CRITICAL)
After implementing each task, you MUST verify it works:
For Rust Code:
# Check it compiles
cargo check --workspace
# Run tests for the specific crate
cargo test -p <crate-name>
# If no tests exist yet, at minimum verify compilation
cargo build --workspace
For Frontend Code:
# Check TypeScript compiles
npm run build
# Run tests if they exist
npm test
For Tauri Integration:
# Verify the app launches
cargo tauri dev
Troubleshooting:
- If compilation fails, fix errors before proceeding
- If tests fail, fix them before marking complete
- If runtime errors occur, debug and resolve
- Document any blockers in PROGRESS.md
Step 5: Update Progress (Only After Verification)
Only after a task is verified working:
-
Update
docs/PROGRESS.md:- Change task status from 🔴 to 🟢
- Add any notes about the implementation
- If blocked, mark as 🔵 and document the blocker
-
If the entire phase is complete:
- Update the milestone status in the Quick Status table
- Add a note in the "Notes & Updates" section
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.
- yesterday First seen · 108 lines · 0 tokens per session scan A 37958c5e74d8
dev is a command published in the GitHub repository advenimus/conduit-desktop (9 stars, last pushed 24d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 737 tokens. 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 commands, from other repositories
generate-prd
Generate a comprehensive Product Requirements Document for the following feature.
plan
Take the following feature description and create a comprehensive, structured implementation plan.
execute-prd
Implement a feature by following a Product Requirements Document step by step.
local-permissions-check
Audit local host/runtime permissions for aidevops on macOS, Linux, Windows, and WSL.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
email-test-suite
../../services/email/email-test-suite.md.