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 fledgeling-co/fledgeling-plugins --skill mac-doctorgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/mac-doctor)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/mac-doctor"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mac-doctor/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/skills/fledgeling-co/fledgeling-plugins/mac-doctor"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mac-doctor.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 | $0.00207 | $0.02949 |
| Opus 5.5 | $0.00083 | $0.01180 |
| Sonnet 5.5 | $0.00041 | $0.00590 |
| Haiku 4.5 | $0.00021 | $0.00295 |
Grade B, and why
mac-doctor 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
them with the command and let the user run it, since most need sudo and launchd How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mac-doctor
Keep a working macOS dev machine from being strangled by its own tooling. Agent CLIs, node and dev servers, Docker, and Xcode each leave debris that is individually reasonable and collectively fatal — this finds it, proves what is safe to remove, removes that, and records the rest.
Two things make this skill rather than a shell alias. First, most of the debris is indistinguishable from live state without checking: a worktree with unpushed commits looks exactly like an abandoned one, a dev server with no peers looks exactly like a forgotten one. Second, the disk fills through accumulation, not events — nothing is ever obviously wrong, so nobody looks until a build fails.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It converts this skill's prohibitions (never system prune -a, never pkill, never kill an idle orphan) into a bound ledger read back off the commands actually run, turns each tier into a counted target list, and requires every reported number to carry the command that produced it. Other models skip it.
Arguments
The invocation may carry an argument, which arrives as ARGUMENTS: <text> at
the end of this file. Match it case-insensitively against the table below,
ignoring any leading dashes — people type --setup, setup and install
interchangeably, and a maintenance tool that argues about punctuation is a
worse tool.
| Argument | Action |
|---|---|
| (none) | Run the longest-cadence tier that is currently overdue — see below |
15m 1h 12h 1d 7d |
Run that tier |
install setup schedule agents |
Install the launchd agents, then show status |
uninstall remove disable |
scripts/install-agents.sh --uninstall |
status agents? scheduled |
scripts/install-agents.sh --status, plus the last ledger entry per tier |
report check dry dry-run |
Survey and explain at 7d depth; change nothing, whatever the thresholds say |
worktrees |
scripts/worktree-audit.sh only, with verdicts |
processes runaway orphans |
scripts/runaway.sh only. Add --apply to act; without it nothing is signalled |
| anything else | Treat it as intent, not a token. "docker is eating my disk" is a 12h scoped to Docker; say which tier you chose and why |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- gemini.md 16 KB
- references/ledger.md 5.2 KB
- references/processes.md 11 KB
- references/reclaim.md 10 KB
- references/scheduling.md 3.5 KB
- references/tiers.md 6.8 KB
- scripts/install-agents.sh 5.2 KB runs code
- scripts/reclaim.sh 8.7 KB runs code
- scripts/runaway.sh 19 KB runs code
- scripts/survey.sh 8.7 KB runs code
- scripts/worktree-audit.sh 9.7 KB runs code
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 Changed 760bbb41c146
- 1mo ago First seen · 212 lines · 207 tokens per session scan B 99b8cbcd34ea
mac-doctor is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 207 tokens to every session and 2,949 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…