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/marcusquinn/aidevopsWrote 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/marcusquinn/aidevops/macos-activity-cleaner)<a href="https://agentmods.dev/commands/marcusquinn/aidevops/macos-activity-cleaner"><img src="https://agentmods.dev/badge/commands/marcusquinn/aidevops/macos-activity-cleaner/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/marcusquinn/aidevops/macos-activity-cleaner"><img src="https://agentmods.dev/badge/commands/marcusquinn/aidevops/macos-activity-cleaner.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 | $0.00010 | $0.00431 |
| Opus 5.5 | $0.00004 | $0.00172 |
| Sonnet 5.5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
macos-activity-cleaner 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.
What it actually says
Execute this request with tools/automation/macos-activity-cleaner.md.
Request: $ARGUMENTS
Modes
| Request | Behaviour |
|---|---|
Empty or audit |
Bounded, read-only audit with ranked recommendations |
audit --quick |
Pressure, processes, persistence, and listeners only |
audit --deep |
Add applications, architecture, extensions, and legacy inventory |
plan |
Compose itemized actions and verification without changing the host |
verify |
Repeat the read-only audit and compare selected findings |
routine |
Non-interactive read-only audit; never prompt, elevate, plan, or mutate |
Required behaviour
- Confirm the host is macOS before collecting evidence.
- Default to read-only, unprivileged inspection and state clearly that no changes were made.
- Do not collect full process arguments, environments, shell history, serial numbers, usernames, or unredacted home paths.
- Treat classifications as evidence, never as permission to quit, disable, move, uninstall, firewall, or restart anything.
- This initial release is audit/plan-only. Never execute remediation, even after approval; provide a reviewed transaction plan for a human or future deterministic helper.
- A remediation plan must bind exact argv, canonical identities, capability impact, administrator requirements, verification, rollback state, and a digest before asking for approval.
- Use durable aidevops quarantine, never Trash as the sole rollback store.
- Do not interrupt active developer services or wildcard listeners merely because they are old, large, long-running, or externally bound.
For TCC or host-app access gaps, use /local-permissions-check. For Spotlight,
Time Machine, or backup exclusions, use /optimise-macos-indexing-backups.
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 · 46 lines · 10 tokens per session scan A ab0a5cd76948
macos-activity-cleaner is a command published in the GitHub repository marcusquinn/aidevops (408 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 431 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
perf-profile.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
debugger
Systematic debugging with TodoWrite and Memory integration.
fix-renovate-mr
Fix renovate issues.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
sparc-debug
🪲 Debugger - You troubleshoot runtime bugs, logic errors, or integration failures by tracing, inspecting, and ...
bug-reporter-agent
Expert in creating comprehensive bug reports. Use when a user needs to report a bug to guide them through capturing all necessary details.