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 skills add laurigates/claude-plugins --skill multi-repo-disciplinegit clone --depth 1 https://github.com/laurigates/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/skills/laurigates/claude-plugins/multi-repo-discipline)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/multi-repo-discipline"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/multi-repo-discipline/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/skills/laurigates/claude-plugins/multi-repo-discipline"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/multi-repo-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.01502 |
| Opus 5 | $0.00019 | $0.00751 |
| Sonnet 5 | $0.00008 | $0.00300 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
multi-repo-discipline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Repo Discipline
Roles and commit boundaries when multiple repositories share a parent workspace. Pairs with configure-plugin:config-sync — that skill propagates mechanical config; this one defines the discipline layer that says who owns what and when a cross-repo commit needs user confirmation.
When to Use This Skill
| Use this skill when… | Skip when… |
|---|---|
| The cwd is inside a parent directory that contains other git repos | Working in a single isolated repo |
A sibling CLAUDE.md names the current repo |
No cross-repo relationship exists |
| Dispatching agents whose scope could span sibling repos | Single-repo agent fan-out |
| Updating a shared spec that other repos consume | Internal change with no downstream |
About to edit a sibling's CLAUDE.md or .claude/ config |
Edits confined to current repo |
Detection Heuristic
Run before applying any discipline:
# Parent directory contains other git repos?
find "$(git rev-parse --show-toplevel)/.." -maxdepth 2 -name .git -type d
# Any sibling CLAUDE.md names this repo by directory name?
grep -l "$(basename "$(git rev-parse --show-toplevel)")" ../*/CLAUDE.md 2>/dev/null
If neither detector produces output, exit silently — the rule does not apply to single-repo work. Do not load discipline that does not apply.
Workspace Roles
Classify every repository in the workspace into one of three roles.
Read-only fixtures
Inputs the current project depends on but must never mutate:
- Licensed datasets (e.g. game data archives, ML training sets)
- Shipped third-party binaries used as reference
- Vendored upstream sources consulted for comparison only
- Historical snapshots of a migrated-away-from system
Discipline: treat as immutable. Never commit to a fixture. If an agent proposes an edit, the edit is a misdirection — redirect to the working repo.
Upstream / downstream pair
Two repositories in the same domain where one derives from the other. Examples:
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.
- today Changed b4711da6d560
- 5d ago First seen · 169 lines · 38 tokens per session scan A db8041181b0f
multi-repo-discipline is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,502 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 2026-09-03.
Other skills, from other repositories
changelog-summarizing
Use this skill when the user asks to summarize, recap, or post about repository changes in the Shopware AI Coding Tools marketplace since a given date — phrases like "write a changelog post for Discord", "recap this week's commits for Slack", "summarize what shipped since 2026-04-01", "draft a release announcement".…
commit-message-writing
Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…
feature-branch-pr-writing
Use this skill when the user asks to write, draft, create, or improve a PR description for a Shopware core repository PR — AND that PR targets a non-trunk feature branch (not trunk itself). Trigger phrases like "write a PR description", "draft the PR", "what should I put in the PR body". The skill detects the target…
pr-description-writing
Use this skill when the user asks to write, draft, create, or improve a PR description, is about to create a PR, or mentions "PR description", "pull request description", or "PR template" — AND that PR targets trunk in the Shopware core repository (shopware/shopware). The skill detects the target and only activates…
changelog
Ingest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis, no edits), status (applied versions), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC…
issue-analyzing
Use this skill when the user asks to analyze a specific GitHub issue, understand what area of code an issue affects, assess an issue's scope, or research the code context around an issue — example triggers like "analyze issue.