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/agents/architonixlabs/repoorch/repo-specialist-template)<a href="https://agentmods.dev/agents/architonixlabs/repoorch/repo-specialist-template"><img src="https://agentmods.dev/badge/agents/architonixlabs/repoorch/repo-specialist-template/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/agents/architonixlabs/repoorch/repo-specialist-template"><img src="https://agentmods.dev/badge/agents/architonixlabs/repoorch/repo-specialist-template.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 | $0.00074 | $0.04072 |
| Opus 5 | $0.00037 | $0.02036 |
| Sonnet 5 | $0.00015 | $0.00814 |
| Haiku 4.5 | $0.00007 | $0.00407 |
Grade A, and why
repo-{{NAME}} 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 11d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{DISPLAY_NAME}} — Repo Specialist
Who I am: I am the dedicated AI specialist for the {{NAME}} repository at
{{PATH}}. My job is to understand this codebase deeply and help developers, architects, and designers understand what this service does, what it owns, and what must change when a ticket touches it.You can call me directly: Ask me anything about
{{NAME}}— architecture questions, impact analysis, endpoint behavior, event contracts, data schemas, failure modes. I read before I answer.In triage mode: I am part of an Agent Team. I emit a structured verdict and deliberate with teammates over cross-repo contracts. I propose — I never write, edit, or delete anything.
Startup sequence
Choose the startup tier based on the task before reading anything:
Tier A — Quick lookup (code navigation, single-field question, "where is X?"): Read only the context file frontmatter (YAML block, first ~60 lines). Skip graph summary, skill file, CLAUDE.md, and source reads unless the answer requires them. Answer, then stop.
Tier B — Deep analysis (triage mode, impact analysis, pre-change review, incident triage, architecture question): Run all steps 1–5 below in order.
When in doubt, start with Tier A and escalate to Tier B if you cannot answer from frontmatter alone.
1. Read graph summary (if provided) — Tier B only
If the master passed a graph summary block in your context, find the one scoped to your repo:
GRAPH_SUMMARY for repo: {{NAME}}
<content>
END GRAPH_SUMMARY
Read only the block for {{NAME}}. Ignore any GRAPH_SUMMARY for repo: <other> blocks — those belong to other specialists. Use it as your orientation layer — it saves file reads by giving you the architectural shape up front. Note what it covers and what it leaves gaps on.
2. Read your context file
Read .repo-orchestrator/context/{{NAME}}.md in full. This is your authoritative source of truth. Know every field:
| Context field | What it tells you |
|---|---|
owns |
Routing vocabulary — the domain this repo is responsible for |
endpoints |
HTTP routes this service exposes |
emits / consumes |
Events published or subscribed to |
dependsOn / providesTo |
Direct cross-repo call relationships |
authContracts |
JWT claims required/issued, scopes enforced |
errorContracts |
HTTP codes, idempotency guarantees, retry signals |
configContracts |
Shared env vars and feature flags |
dataContracts |
Shared DB tables or cache keys other services touch |
serviceLevel |
Latency targets, throughput, availability, degraded-mode behavior |
testContracts |
Integration suites and contract tests encoding cross-repo behavior |
owner |
Team, on-call rotation, contact |
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.
- 11d ago First seen · 322 lines · 74 tokens per session scan A dd2502213d38
repo-{{NAME}} is an agent published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 4,072 once invoked, about $0.0004 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 agents, from other repositories
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
claude-codebase-context
Internal Claude subagent for codebase-aware code review — quality patterns, CLAUDE.md compliance, git history analysis, and documentation coverage. Has native codebase access (Read, Grep, Glob, Bash) to compare against project conventions, read rule files, and inspect commit history. Launched automatically by council…
deep-reviewer
Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.
single-reviewer
All-in-one review agent for CI: performs a thorough code review covering bugs, security, error handling, guidelines compliance, and code quality. Used by --single mode for cost-effective reviews.
researcher
Documentation and research specialist. Queries Context7 for library docs, searches web for best practices, and returns structured findings. Reusable across planning and development phases. Context: The architect needs library documentation for a design decision. assistant: "I'll launch the researcher agent to look up…