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/architonixlabs/RepoOrchWrote 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/architonixlabs/repoorch/repo-orch-edit)<a href="https://agentmods.dev/commands/architonixlabs/repoorch/repo-orch-edit"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-edit/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/architonixlabs/repoorch/repo-orch-edit"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-edit.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 | $0.00029 | $0.00668 |
| Opus 5 | $0.00015 | $0.00334 |
| Sonnet 5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
repo-orch-edit 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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-orch-edit <repo>
Open and guide editing of a specific repo's context document.
Usage: /repo-orch-edit auth-service
Step 1 — Resolve the repo
Read .repo-orchestrator/registry.json. Find the entry with name == <repo>. If not found, list available names and stop.
Get the contextFile path (e.g., .repo-orchestrator/context/auth-service.md). If the file does not exist, stop: "Context file not found. Run /repo-orch-init first."
Step 2 — Present the file
Read and display the current content of the context file.
Then offer guidance:
Context file for <repo>: <contextFile>
Edit this file directly in your editor, or I can help you update specific sections.
Key fields for routing (in the YAML frontmatter):
owns: domain keywords — what problem areas does this repo own?
endpoints: HTTP routes this repo exposes
emits: events this repo publishes
consumes: events this repo subscribes to
Contract fields (used by specialists during analysis):
authContracts: JWT claims required/issued, RBAC scopes
errorContracts: HTTP codes, idempotency, retry semantics
configContracts: shared env vars and feature flags
dataContracts: shared DB tables or cache keys
serviceLevel: latency targets, throughput, availability
testContracts: integration suite commands, contract test paths
Ask me to update any section, e.g.:
"Add 'oauth' to owns"
"The /api/users endpoint was renamed to /api/v2/users"
"We now consume the order.paid event"
"Set retryOn to [503, 429]"
When done editing, say "done" and I'll ingest the changes into the registry.
Step 3 — Apply requested edits (if any)
If the user asks for specific changes, apply them to the context file:
- For frontmatter fields: parse the YAML, update the field, re-serialize.
- For prose sections: locate the heading and update the content.
- Always show the diff before writing: "I'll make these changes: [diff]. Proceed? [y/N]"
Step 4 — Ingest on completion
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.
- 12d ago First seen · 79 lines · 29 tokens per session scan A 0f7972beb607
repo-orch-edit is a command published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 668 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
develop
Implement skill development issues with TDD-governed workflow.
update
Update the swarm plugin to the latest version.
launch
Interactively launch an agent team with guided setup.
dev-task
Create an agent team to develop: Developer teammate + Code-tester teammate + QA-tester teammate + Reviewer teammate + Researcher subagent → implements .dev/cdt/plans/plan-$TIMESTAMP.md in waves.