cross-repo-cache

cross-repo-cache is a skill for Claude Code from closedloop-ai/claude-plugins. It costs 81 tokens per session (717 once invoked), scanned A, original, Apache-2.0.

A cross-repository cache that records the current commit of related repositories and checks whether coordinator results can be reused.

In plain words
What is it for?
Use it before discovering related repositories to decide whether to use cached coordinator results or run the coordinator again.
Why use it?
It avoids repeating cross-repository analysis when the peer repositories have not changed. Changed repositories invalidate the saved results.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the code plugin — 15 skills, 7 commands, 23 agents, 7 hooks shipped together

Good fit Use it before discovering related repositories to decide whether to use cached coordinator results or run the coordinator again.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/closedloop-ai/claude-plugins/cross-repo-cache
Install

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.

Any agent
npx skills add closedloop-ai/claude-plugins --skill cross-repo-cache
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Or install code, the plugin that ships this one along with the rest of its 15 skills, 7 commands, 23 agents, 7 hooks.

Wrote 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.

agentmods badge for cross-repo-cache

README.md
[![agentmods](https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cross-repo-cache.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/cross-repo-cache)
Your own site
<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/cross-repo-cache"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/cross-repo-cache.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.00717
Opus 5 $0.00041 $0.00358
Sonnet 5 $0.00016 $0.00143
Haiku 4.5 $0.00008 $0.00072

Measured today against content hash 1cb1750c92b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cross-repo-cache 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_cross_repo_cache.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/code/skills/cross-repo-cache/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Repo Cache Skill

Check whether prior cross-repo coordinator results are still valid, avoiding redundant Sonnet agent launches when peer repositories haven't changed.

When to Use

Activate this skill at the start of Phase 1.4.1 (Discover peers), before launching @code:cross-repo-coordinator. If the cache is fresh, skip the coordinator and use cached results.

Usage

Check Cache (Phase 1.4.1)

bash ${CLAUDE_SKILL_DIR}/scripts/check_cross_repo_cache.sh <WORKDIR>

Stamp Cache (after coordinator completes)

After the cross-repo-coordinator runs successfully, stamp the cache:

# Compute hash of peer repo states
if [ -f ".workspace-repos.json" ]; then
  repo_hashes=""
  for repo_path in $(python3 -c "import json; [print(r['path']) for r in json.load(open('.workspace-repos.json')) if r.get('path')]" 2>/dev/null); do
    [ -d "$repo_path/.git" ] && repo_hashes="$repo_hashes$repo_path:$(git -C "$repo_path" rev-parse HEAD 2>/dev/null || echo unknown) "
  done
  echo "$repo_hashes" | shasum -a 256 > $WORKDIR/.cross-repo-hash
else
  shasum -a 256 $WORKDIR/.cross-repo-needs.json > $WORKDIR/.cross-repo-hash
fi

Interpreting Output

Cache Hit

CROSS_REPO_CACHE_HIT
status: NO_CROSS_REPO_NEEDED | CAPABILITIES_IDENTIFIED
capabilities:
  - peer-name: capability description

Action:

  • If status is NO_CROSS_REPO_NEEDED: Mark 1.4.x phases complete, proceed to Phase 2
  • If status is CAPABILITIES_IDENTIFIED: Skip coordinator, proceed to Phase 1.4.2 with cached capabilities

Cache Miss

CROSS_REPO_CACHE_MISS
reason: <why the cache is stale or missing>

Action: Launch @code:cross-repo-coordinator as normal. After it completes, stamp the cache.

How Freshness Works

The script hashes the git HEAD commit of each peer repository listed in .workspace-repos.json. If any peer has new commits, the hash changes and the coordinator re-runs. This correctly handles the case where a peer repo is updated between iterations.

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. today First seen · 78 lines · 81 tokens per session scan A 1cb1750c92b8

Subscribe to this mod's changes

cross-repo-cache is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 717 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 2026-09-07.

Related

Other skills, from other repositories

session-end

Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.

Kanevry/session-orchestrator · 54 tokens

session-start

Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status. Then presents structured findings with recommendations for user alignment before creating a wave plan. Triggered by /session…

Kanevry/session-orchestrator · 70 tokens

ops-standup

Cross-repo morning briefing. Aggregation of recent commits, PRs, CI, blockers and priorities of the day. Trigger when the user wants a standup, an activity summary, or to know what happened.

christopherlouet/claude-base · 48 tokens

work-batch

Sequential execution of user stories from a PRD file. Autonomous mode that implements and commits each story one by one. Trigger when the user wants to process a backlog, execute multiple stories, or launch an autonomous mode.

christopherlouet/claude-base · 47 tokens

dev-finish

Close out a session — summarise what changed, capture what was learned, and prepare the commit.

ToruAI/toru-claude-agents · 24 tokens

conventional-commit

Use this skill any time the user asks for a git commit. Writes messages in Conventional Commit format.

siracalaks/claude-code-antigravity-a-z · 25 tokens