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.
git clone --depth 1 https://github.com/gf-labs/claude-toolboxWrote 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/gf-labs/claude-toolbox/atlas)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/atlas"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/atlas/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/commands/gf-labs/claude-toolbox/atlas"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/atlas.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 | $0.00000 | $0.01289 |
| Opus 5.5 | $0.00000 | $0.00516 |
| Sonnet 5.5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
atlas 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collect context
Run this once. It parses the arguments, resolves scope, dispatches to the backing collectors, renders, and emits sectioned output. Do NOT re-run collectors, re-derive enumeration, or re-render — print what it printed.
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-atlas.py $ARGUMENTS
Output is delimited by === SECTION === markers:
| Section | Meaning |
|---|---|
=== REQUEST === |
how the arguments parsed (FACETS/PROJECT/DIR/DEPTH/SCOPE/STALE). If it has an ERRORS: line, surface it and stop. |
=== ERROR === |
--project or --dir did not resolve; show the message and stop. |
=== ATLAS === |
the fully rendered atlas (emitted when ≥2 project facets are requested — including the bare default). First line is a ## header; every other line is pre-aligned final text. |
=== PROJECTS === |
(single-facet mode only) TSV from collect-status: GROUP PROJECT BRANCH LOCAL_BRANCHES SESSIONS CHANGES LAST_COMMIT MEMORY_LINES MEMORY_STATUS BACKLOG_ITEMS LAST_SNAPSHOT SESSIONS_SINCE LAST_SESSION_LOG LOG_ENTRIES LAST_COMMIT_DATE, plus # ORPHANED_KEYS / # UNSCOPED_KEYS blocks. |
=== SESSIONS === |
(single-facet) TSV PROJECT SESSION TITLE LAST_EVENT — newest last-event first within each project; — = unnamed/no events. |
=== MEMORY === |
(single-facet) same rows as PROJECTS — render the memory columns (MEMORY_LINES / MEMORY_STATUS / LAST_SNAPSHOT / LAST_SESSION_LOG / LOG_ENTRIES). |
=== PLANS === |
(single-facet) plan inventory: file.md NL [project] Title + → first bullet. |
=== SPECS === |
(single-facet) TSV PROJECT KIND STATUS FILE TITLE — in-repo docs/superpowers specs and plans; STATUS live/done. |
=== PLUGINS === |
plugin cache drift / sync lines. |
=== CLAUDE.MD === |
(single-facet) TSV CONTAINER PROJECT CLAUDE_MD_DEPTH MEMORY_LINES MEMORY_STATUS CHAIN — the »-joined inheritance chain. |
=== STALE === |
(only with --stale) ORPHANED/UNSCOPED key rows, or (none). |
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.
- 1mo ago First seen · 73 lines · 0 tokens per session scan A 725c8c5296bc
atlas is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,289 tokens. 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
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
show
Show this project's saved Recall context (.recall/context.md).
handoff
Write a session handoff document for continuity.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.