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-selectgit 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 | $0.00693 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
devteam-select 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTeam Select Command
Command: /devteam:select
Select a plan to work on. The selected plan becomes the active plan for /devteam:implement.
Usage
/devteam:select 2 # Select by number (from /devteam:list)
/devteam:select notifications # Select by name (partial match)
/devteam:select feature-dark-mode # Select by full plan ID
Your Process
Step 1: Identify Plan
By number:
/devteam:select 2
→ Look up plan #2 from index
By partial name:
/devteam:select dark
→ Search plans for "dark" in name/ID, confirm if multiple matches
By full ID:
/devteam:select feature-dark-mode
→ Direct lookup
Step 2: Validate Plan
Check plan status:
planned→ Ready to startin_progress→ Can resumecomplete→ Warn user (can re-run but likely not needed)archived→ Ask to unarchive firstfailed→ Ask to reset circuit breaker
Step 3: Update Active Plan
# Update index.json
active_plan: feature-dark-mode
# Update pointer file
echo "feature-dark-mode" > .devteam/active-plan.txt
Step 4: Show Confirmation
✅ Selected plan: Dark Mode Support (feature-dark-mode)
Type: feature
Parent: project-taskmanager
Status: planned
Sprints: 1 total, 0 completed
Tasks:
📋 TASK-001: Define dark mode color tokens
📋 TASK-002: Create theme context
📋 TASK-003: Update components for theme
📋 TASK-004: Add theme toggle UI
Next steps:
• /devteam:implement Execute this plan
• /devteam:plan Modify the plan
• /devteam:list See all plans
Disambiguation
If partial match finds multiple plans:
/devteam:select mode
Output:
Multiple plans match "mode":
1. feature-dark-mode (Dark Mode Support)
2. feature-offline-mode (Offline Mode)
Enter number to select, or use full ID:
>
Error Cases
Plan not found:
❌ No plan found matching "xyz"
Available plans:
1. Task Manager App (project)
2. Push Notifications (feature)
3. Dark Mode Support (feature)
Use /devteam:list to see all plans.
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 · 136 lines · 0 tokens per session scan A 072a4f3a7550
devteam-select 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 693 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).