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/michael-harris/devteam/devteam-plangit clone --depth 1 https://github.com/michael-harris/devteamWhat 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 | $0.04736 |
| Opus 5 | $0.00000 | $0.02368 |
| Sonnet 5 | $0.00000 | $0.00947 |
| Haiku 4.5 | $0.00000 | $0.00474 |
Grade A, and why
devteam-plan 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 — 727 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTeam Plan Command
Command: /devteam:plan [options]
Conduct interactive requirements gathering, research the codebase, create a PRD, and generate a development plan with tasks and sprints.
Usage
/devteam:plan # Start interactive planning
/devteam:plan "Build a task manager" # Start with description
/devteam:plan --feature "Add dark mode" # Plan a feature for existing project
/devteam:plan --from spec.md # Load from single spec file
/devteam:plan --from specs/ # Load from folder of spec files
/devteam:plan --from existing # Auto-detect existing docs in project
/devteam:plan --skip-research # Skip research phase
Options
| Option | Description |
|---|---|
--feature "<desc>" |
Plan a feature for existing project |
--from <path> |
Load from spec file or folder |
--skip-research |
Skip codebase research phase |
--skip-interview |
Skip interview (use with --from) |
File-Based Specification Support
Supported File Formats
| Format | Extensions | Best For |
|---|---|---|
| Markdown | .md |
Human-readable specs, PRDs |
| YAML | .yaml, .yml |
Structured specs, existing PRDs |
| JSON | .json |
API specs, structured data |
| Plain Text | .txt |
Simple requirements lists |
.pdf |
Formal documents (extracted) |
Single File Mode (--from file.md)
Reads a specification file and extracts:
- Project description
- Features/requirements (from headers, lists)
- Technical constraints
- User stories
- Acceptance criteria
Example Input (project-spec.md):
# Task Manager App
## Overview
A simple task management app for teams.
## Features
- User authentication with OAuth
- Create, edit, delete tasks
- Assign tasks to team members
- Due date reminders
## Technical Requirements
- Backend: FastAPI
- Database: PostgreSQL
- Frontend: React + TypeScript
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 · 727 lines · 0 tokens per session scan A f91893afcd1c
devteam-plan is a command published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,736 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 2026-08-30.
Other commands, from other repositories
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
map
View, rebuild, or query the codebase dependency map.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
double-check
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.
code-explain
Explain complex code through clear narratives and visual diagrams.
health
Run documentation health checks (freshness, links, drift, cross-doc consistency).