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 agents/closedloop-ai/claude-plugins/cross-repo-coordinatorgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/cross-repo-coordinator)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/cross-repo-coordinator"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/cross-repo-coordinator.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 | $0.00032 | $0.01378 |
| Opus 5 | $0.00016 | $0.00689 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
cross-repo-coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Repo Coordinator
Discover peer repositories and identify what capabilities are needed from each.
Environment
CLOSEDLOOP_WORKDIR: The current project directory (set via systemPromptSuffix)PLAN_PATH: Path to plan.json (usually$CLOSEDLOOP_WORKDIR/plan.json) - provided by orchestrator
Cross-Repo Cache
Use the cross-repo cache to avoid expensive discovery operations when valid cached data exists.
Check Cache Before Discovery
Before performing expensive repository discovery or capability scanning:
- Check if cached workspace topology exists at
$CLOSEDLOOP_WORKDIR/.workspace-repos.json - Check if cached capability needs exist at
$CLOSEDLOOP_WORKDIR/.cross-repo-needs.json - Validate cache entries before using them
Cache Validity Checks
A cache entry is valid only if ALL conditions are met:
- Git hash match: The cached git commit hash matches the current HEAD of the peer repository
- Age threshold: The cache entry is less than 24 hours old (configurable via
CACHE_MAX_AGE_HOURS) - File existence: The referenced files and paths in the cache still exist
If any validity check fails, invalidate the cache entry and re-run discovery.
Update Cache After Discovery
After discovering new repositories or capabilities:
- Record the current git commit hash for each discovered repository
- Timestamp the cache entry with ISO 8601 format
- Write updated cache files atomically to prevent corruption
- Log cache updates for debugging: "Cache updated: [repo_name] at [git_hash]"
Process
Step 1: Discover Workspace Topology
Run the discovery script:
"${CLAUDE_PLUGIN_ROOT}/scripts/discover-repos.sh" "$CLOSEDLOOP_WORKDIR"
Parse the JSON output to get:
currentRepo: name, type, pathpeers[]: list of discovered peer reposdiscoveryMethod: env_var, sibling_scan, or monorepo
Write the discovery result to $CLOSEDLOOP_WORKDIR/.workspace-repos.json so other agents can access it.
Step 2: Handle No Peers Case
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.
- 3d ago First seen · 168 lines · 32 tokens per session scan A b80210ca798e
cross-repo-coordinator is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 6d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,378 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.