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 skills/ryanb/dotfiles/fix-allnpx skills add ryanb/dotfiles --skill fix-allgit clone --depth 1 https://github.com/ryanb/dotfilesWhat 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 | $0.00023 | $0.01496 |
| Opus 5 | $0.00012 | $0.00748 |
| Sonnet 5 | $0.00005 | $0.00299 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
fix-all 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix All Review Issues
Automatically find and fix all issues reported by bin/claude-review --print.
Step 1: Run the review
Run bin/claude-review --print to get the list of issues. If the command doesn't exist or fails, report back to the user and stop.
Step 2: Print the full review output verbatim
This is a required, non-optional step. Do not skip it.
Before reading any file, spawning any sub-agent, or making any edit, emit a plain-text message to the user containing the entire, unmodified stdout from bin/claude-review --print.
Rules for this step:
- Paste the output verbatim. Do not summarize, truncate, paraphrase, reorder, or omit any issue — including issues surfaced in "prior review runs" or notes.
- Do not collapse multiple issues into a "note" or parenthetical. Every issue the review reported must appear in full, with its severity, file:line, and description.
- Do not wrap it in commentary beyond a one-line header like
=== Code Review ===. - Do not stop or end the turn after printing. Immediately continue to Step 3 in the same turn — the printed output is informational for the user, not a checkpoint.
Step 3: Parse the issues
Parse the review output into individual issues. Each issue is separated by a line of dashes (--------------------------------------------------) and follows this format:
Issue N (Severity): file_path:line_number
Description...
Severity is one of: Critical, Warning, Suggestion.
If the output says "No issues found." then report that to the user and stop.
Step 4: Fix issues sequentially
Fix each issue, processing them one at a time, sequentially (not in parallel) to avoid conflicts between fixes. The current working directory is the project root.
Decide whether to fix inline or via a sub-agent:
- Inline (in this session): small, localized fixes — a typo, a one-line change, a rename, a trivial guard clause. These don't warrant the overhead of a sub-agent.
- Sub-agent: larger or context-heavy fixes — multi-file changes, fixes requiring significant exploration, or anything that would clutter the main context. Spawning a sub-agent keeps that work isolated.
What ships with it
1 file 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.
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.
- 2d ago First seen · 100 lines · 23 tokens per session scan A 22711c0f582b
fix-all is a skill published in the GitHub repository ryanb/dotfiles (2,399 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 1,496 once invoked, about $0.0001 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
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
commit
Commit message formatting and guidelines.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
keploy-pr-workflow
Guide for creating PRs and issues on keploy repositories — PR format, customer-data hygiene, commit conventions, sign-off. Invoke when the user asks to open, update, or review a pull request or issue, when preparing a commit that will land in main, or whenever a change is about to leave the local machine.