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 bendrucker/claude --skill historygit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/history)<a href="https://agentmods.dev/skills/bendrucker/claude/history"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/history.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 | $0.00077 | $0.00807 |
| Opus 5 | $0.00039 | $0.00404 |
| Sonnet 5 | $0.00015 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
atuin:history 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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell History
Report shell activity from atuin's local capture. This skill only reads. Never run subcommands that modify history (atuin delete, atuin search --delete, atuin import).
Arguments are search terms: start with atuin search $ARGUMENTS.
CLI Queries
The default path. atuin search [query] prints matching commands, newest first. Useful flags:
--after "2 days ago"/--before "2026-07-01": date bounds, human phrases work-c/--cwd <dir>: commands run in a directory (--exclude-cwdto invert)-e/--exit <code>/--exclude-exit <code>: filter by exit code (--exclude-exit 0finds failures)--limit <n>: cap the result count-r: oldest first instead of newest first-f/--format '{time} {command}': also{directory},{exit},{duration},{relativetime},{user},{host}--cmd-only: bare command text--search-mode <prefix|full-text|fuzzy|skim>:full-textfor exact substring matches, overriding the fuzzy default--include-duplicates: repeated identical commands otherwise collapse to the latest
atuin stats [today|week|month|year] aggregates the period: top commands with counts. -c <n> sets top-N, -n 2 counts command pairs (sequences) instead of single commands.
atuin history list dumps everything, and takes --cmd-only and -f too.
Sandbox
Query subcommands work sandboxed: the sandbox grants writes to ~/.local/share/atuin because atuin opens its metadata db read-write even for searches. Network subcommands (atuin status, sync, login) fail sandboxed. They are never needed to answer history questions, so don't escalate.
DuckDB
For aggregations the CLI can't express (frequency by directory, time-bucketed histograms, joins against other data):
duckdb -c "INSTALL sqlite; LOAD sqlite;
ATTACH '$HOME/.local/share/atuin/history.db' AS atuin (TYPE sqlite, READ_ONLY);
SELECT ...;"
Use $HOME, not ~ (DuckDB does not expand tildes). READ_ONLY is mandatory: the db is WAL-mode with live writers. INSTALL sqlite is a local no-op once the extension is cached. A machine without the cache must run it unsandboxed once, since the extension host is not sandbox-reachable.
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.
- 7d ago First seen · 59 lines · 77 tokens per session scan A 8440e5858d75
atuin:history is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 807 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…