Borrowing it
Nothing to install: this file belongs to mmyslin/sideboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mmyslin/sideboard/main/CLAUDE.mdgit clone --depth 1 https://github.com/mmyslin/sideboardWrote 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/instructions/mmyslin/sideboard/claude-md)<a href="https://agentmods.dev/instructions/mmyslin/sideboard/claude-md"><img src="https://agentmods.dev/badge/instructions/mmyslin/sideboard/claude-md/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/instructions/mmyslin/sideboard/claude-md"><img src="https://agentmods.dev/badge/instructions/mmyslin/sideboard/claude-md.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 | $0.00893 | $0.00893 |
| Opus 5.5 | $0.00357 | $0.00357 |
| Sonnet 5.5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
sideboard CLAUDE.md 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 2mo 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.
What it actually says
Sideboard — working notes for Claude
Sideboard's own roadmap lives in GitHub Issues (mmyslin/sideboard). The project
is GitHub-only — there is no roadmap.json / local-file mode.
- Manage roadmap items via
gh—gh issue create/edit/close/reopen. Swimlane (backlog vs in_progress) + card order live in.sideboard/meta.json(committed sidecar);done= a closed issue; a card's#Nis its GitHub issue number. The sidecar is reconciled automatically by the router from the issues + your drag/reorder — don't hand-edit it. - Sequences — ordered dependency chains of ≥2 issues (in
.sideboard/meta.json), managed via the/sideboard:roadmap-sequencecommand + the router's/api/seq/*. Honor them when working: starting a sequenced issue with an unfinished predecessor → check in first; closing one → suggest the next. Seeskills/sideboard/SKILL.md→ "Acting on a sequenced issue". - Repo layout is the plugin layout (#12):
commands/(thesideboard:slash commands),skills/sideboard/SKILL.md,scripts/(router + shell scripts),hooks/hooks.json, and.claude-plugin/{plugin,marketplace}.json.install.shis the legacy installer; it copies out ofskills/+scripts/. - Releasing (version-bump convention): once listed in the community
marketplace, Anthropic's CI auto-advances the catalog's commit-SHA pin on every
push — but users only receive an update when
versionin.claude-plugin/plugin.jsonchanges. So push freely (docs, refactors, WIP); bumpversion(semver) only when you want users to get the change — that bump is the deliberate "ship it" lever. Keep the marketplace entry free of aversionfield soplugin.jsonstays the single source of truth. No re-submission is needed for updates (whether each push is re-screened is undocumented). - Run the board:
scripts/sideboard-up.sh— starts the router (scripts/sideboard_router.py) on :7777, which follows the active project and serves its board. Then open the pane once per project (or use/sideboard:roadmap). Under the plugin theSessionStarthook launches it for you. - Multi-project / auto-follow (#35): one router serves ALL projects. A global
Claude Code hook (
scripts/sideboard-active.sh, on SessionStart + UserPromptSubmit) POSTs the session TITLE to the router, which maps title→project dir (~/.claude/sideboard-projects.json, token-matched, editable) and switches the served board. cwd is useless here (always $HOME) — title is the only signal. The preview pane is per-session, so open it once per project with/sideboard:roadmap; thereafter switching projects (send a message) makes each project's pane show its own roadmap. - Discovery keys off
.sideboard/meta.json: a project is only picked up once that sidecar exists. Bootstrap a new repo withmkdir -p .sideboard && printf '{"schema": 2}\n' > .sideboard/meta.json(commit it); the router reconciles it from the issues on first sync. - Design + phases:
docs/github-sync-design.md(#15). Distribution: shipped as a Claude Code plugin (#12) — community-marketplace submission is the remaining discoverability step. Naming decision: #39.
The global sideboard skill (skills/sideboard/SKILL.md) documents this same
GitHub-only model — this file is just the repo-specific pointer.
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.
- 2mo ago First seen · 51 lines · 893 tokens per session scan A 8746cc779f35
sideboard CLAUDE.md is an instructions file published in the GitHub repository mmyslin/sideboard (2 stars, last pushed 2mo ago), licensed MIT. It adds 893 tokens to every session, about $0.0036 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.