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/openshift-online/agent-control-plane/trex.project.initgit clone --depth 1 https://github.com/openshift-online/agent-control-planeWrote 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/openshift-online/agent-control-plane/trex.project.init)<a href="https://agentmods.dev/commands/openshift-online/agent-control-plane/trex.project.init"><img src="https://agentmods.dev/badge/commands/openshift-online/agent-control-plane/trex.project.init.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 | $0.00000 | $0.01000 |
| Opus 5 | $0.00000 | $0.00500 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
trex.project.init 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 4d 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.
This is a copy
100% identical to trex.project.init — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Init
Validate that this TRex-spawned project is in a healthy, working state. This command is idempotent — it succeeds if everything is already running and correct, and only fails if something is genuinely broken.
Use the TodoWrite tool to track each phase as you work through it.
Phase 1: Naming Consistency Audit
Scan all .go, .yaml, and .md files (skip go.sum) for template leftovers from the TRex scaffold. Flag any of the following:
| Pattern | Why It's Wrong |
|---|---|
"My Service" or "My service" |
Placeholder title never renamed |
"Dinosaur" or "dinosaur" (outside go.mod/go.sum imports) |
TRex example entity left behind |
"rh-trex" in description strings or comments (import paths are fine) |
Template origin leaking into runtime |
[email protected] |
Template default contact |
api.openshift.com or api.stage.openshift.com in server URLs |
Template default servers |
"template" in code comments suggesting unfinished customization |
Scaffold language not cleaned up |
"placeholder" in comments |
Scaffold language not cleaned up |
Stub TODO comments (e.g., // TODO: Add ... when needed) in otherwise empty files |
Empty scaffold files |
Action: Report every finding with file, line number, and the problematic text. Do NOT auto-fix — present the findings to the user and ask how they want each category handled (rename, remove, or keep).
Phase 2: Dependency Resolution
go mod tidy
Verify no errors. If go.sum changes, that's fine — it means dependencies were stale.
Phase 3: Build the Binary
make binary
This must succeed with zero errors. If it fails:
- Report the exact error output
- Diagnose the root cause (missing dependency, type error, import cycle, etc.)
- Ask the user before attempting any fix
Phase 4: Database Setup (Idempotent)
- Check if the PostgreSQL container is already running:
docker ps --filter name=ambient-api-server-postgres --format "{{.Names}} {{.Status}}"
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.
- 4d ago First seen · 141 lines · 0 tokens per session scan A ba5f20fb5df6
trex.project.init is a command published in the GitHub repository openshift-online/agent-control-plane (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,000 tokens. A static security scan graded it A with 0 findings. It is 100% identical to trex.project.init, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
research
Research a technical or product question.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.