Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atuljha23/holocron/plugin install holocronWrote 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/commands/atuljha23/holocron/onboard)<a href="https://agentmods.dev/commands/atuljha23/holocron/onboard"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/onboard.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 5.1 | $0.00031 | $0.00667 |
| Opus 5 | $0.00015 | $0.00333 |
| Sonnet 5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
onboard 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 6d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/holocron:onboard
Draft (or refresh) a CLAUDE.md at the repo root tailored to this project.
Detect stack
Inspect the repo root and key subdirectories. Check for:
package.json— detect framework hints (react, next, vue, svelte, express, fastify, nestjs, remix), test runner (jest, vitest, mocha, playwright, cypress), lint (eslint, biome), typechecker (tsc).pyproject.toml/setup.cfg/requirements*.txt— detect Django, Flask, FastAPI, pytest, ruff, mypy.go.mod— detect web framework (gin, chi, echo, fiber), test tooling.Gemfile— Rails / Sinatra.Cargo.toml— web framework if any,cargo test.pom.xml/build.gradle[.kts]— Java / Kotlin, Spring Boot.composer.json— PHP / Laravel.- Infra:
Dockerfile,docker-compose.yml,.github/workflows/,terraform/,helm/,k8s/.
Use ${CLAUDE_PLUGIN_ROOT}/contexts/<role>.md for baseline context:
- frontend-heavy repo (React/Vue/Svelte, no server) →
contexts/frontend.md - backend-heavy repo (API server, no client) →
contexts/backend.md - test-centric or QA tooling repo →
contexts/qa.md - mixed / monorepo →
contexts/polyglot.md
Also load applicable files from ${CLAUDE_PLUGIN_ROOT}/rules/ based on detected signals.
Draft CLAUDE.md
Fill in the template at ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md.tmpl with:
- Project name (from
package.json/pyproject.toml/ repo folder name). - Detected stack (one line per language/framework found).
- Commands the LLM should prefer (
npm test,pytest -q,go test ./...). - Recommended agents: a shortlist of
@architect,@frontend-engineer,@backend-engineer,@qa-engineer, etc. that match the stack. - Recommended holocron commands for this stack (e.g. always include
/holocron:a11yfor frontend projects).
If CLAUDE.md already exists
Do NOT overwrite. Diff against the detected stack, list what would be added or updated, and ask before writing. With --dry-run, never write — only print the proposed content.
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.
- 6d ago First seen · 54 lines · 31 tokens per session scan A 4b747865991b
onboard is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 667 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 2026-08-31.
Other commands, from other repositories
learn
Learn Claude Code best practices and capture lessons into persistent memory.
insights
Surface patterns from your pro-workflow learnings and session history.
handoff
Generate a structured handoff document that another Claude session (or your future self) can consume immediately to continue where you left off.
wiki
Build, query, and maintain long-lived knowledge bases. Each wiki = markdown folder + SQLite FTS5 shadow index. Survives sessions, indexes auto-load on SessionStart.
commit
Create a well-crafted commit after running pro-workflow quality checks.
context-optimizer
Diagnose and fix context window problems.