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 commands/metabuilder-labs/tokenjam/onboardgit clone --depth 1 https://github.com/Metabuilder-Labs/tokenjamWrote 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/metabuilder-labs/tokenjam/onboard)<a href="https://agentmods.dev/commands/metabuilder-labs/tokenjam/onboard"><img src="https://agentmods.dev/badge/commands/metabuilder-labs/tokenjam/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 | $0.00049 | $0.00416 |
| Opus 5 | $0.00024 | $0.00208 |
| Sonnet 5 | $0.00010 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade B, and why
onboard scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Otherwise, summarize what onboarding wired into `~/.claude/settings.json`: What it actually says
Check for the tj CLI
!command -v tj >/dev/null 2>&1 && echo "found: $(tj --version 2>&1)" || echo "NOT_FOUND"
Run onboarding (only if tj is on PATH)
!command -v tj >/dev/null 2>&1 && tj onboard --claude-code --reconfigure --plan "${ARGUMENTS:-api}" --budget 0 --backfill-days 30 --analysis-span 30d 2>&1 || echo "Skipped: tj is not installed."
Instructions
If the check above printed NOT_FOUND or the run was skipped, tell the user to install TokenJam first — npx tokenjam@latest or pipx install tokenjam — then re-run /onboard. Nothing here requires an account or network service; TokenJam reads Claude Code's own OTel telemetry locally.
Otherwise, summarize what onboarding wired into ~/.claude/settings.json:
- the zero-token statusline (
tj statusline) — costs no model quota, shows context re-read % after every turn - the resume-brief
SessionStarthook - the local OTel ingest endpoint TokenJam listens on
It used plan ${ARGUMENTS:-api} (the generic default if no argument was given) to frame dollar figures. If the user's actual Claude plan is a subscription tier, tell them they can re-run /onboard <plan> (e.g. /onboard max_20x) at any time — it's idempotent and safe to repeat.
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.
- 4d ago First seen · 23 lines · 49 tokens per session scan B 09d5192f4413
onboard is a command published in the GitHub repository Metabuilder-Labs/tokenjam (106 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 416 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
tma1-peer
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
review
Review proposed ADRs for lifecycle progression — accept implemented decisions, deprecate stale ones, archive trivial ones.
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
swarm-planner
Generates a structured execution plan with dependency tracking using the Swarms-inspired planning methodology.