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.
git clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/commands/telus-labs/stagecraft/devteam)<a href="https://agentmods.dev/commands/telus-labs/stagecraft/devteam"><img src="https://agentmods.dev/badge/commands/telus-labs/stagecraft/devteam/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/commands/telus-labs/stagecraft/devteam"><img src="https://agentmods.dev/badge/commands/telus-labs/stagecraft/devteam.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 | $0.00071 | $0.00480 |
| Opus 5.5 | $0.00028 | $0.00192 |
| Sonnet 5.5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
devteam 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.
What it actually says
/devteam
Drive the Stagecraft pipeline.
Input
The text after /devteam is interpreted as a subcommand. Examples:
/devteam stage requirements— render the PM stage prompt/devteam stage build— render all four build workstream prompts/devteam merge build— merge per-workstream gates into the stage gate/devteam stages— list known stages/devteam hosts— list installed host adapters
If the input is empty, ask the user which stage they want to run, then
re-invoke with stage <name>.
Behavior
- Run
devteam <subcommand>in a Bash tool call. (Installdevteamglobally withnpm linkfrom the Stagecraft repo if it's not on the user's PATH.) - The CLI prints one stage prompt per workstream (one for single-role
stages, N for multi-role stages like
build). - For each printed prompt:
- Identify the named subagent from the prompt (
.claude/agents/<name>.md). - Invoke that subagent with the prompt's body.
- Wait for it to write the workstream gate at
pipeline/gates/<workstream-id>.json.
- Identify the named subagent from the prompt (
- For multi-role stages, after all workstream gates exist, run
devteam merge <stage>to produce the stage-level merged gate. - Report status back to the user and ask whether to proceed to the next stage.
Gate identity (per Stagecraft contract F)
Workstream gates carry: stage, workstream, status, track,
timestamp, blockers, warnings, plus stage-specific fields.
The orchestrator adds orchestrator and host at write/validation time.
Do NOT write agent — it has been removed.
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 · 49 lines · 71 tokens per session scan A 33eec0c83af8
devteam is a command published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed 19d ago), licensed MIT. It adds 71 tokens to every session and 480 once invoked, about $0.0003 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 commands, from other repositories
set-tracker
Set the issue tracker for the current project.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
dashboard-session-fork
Fork a session into a new one. Usage /dashboard:session-fork.
dashboard-session-hide
Hide a session from the dashboard list. Usage /dashboard:session-hide.
os-meeting
A command for listing active AI Team OS meetings, creating a meeting, or viewing a meeting’s messages and details.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.