Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add fivol/claude-make-better/plugin install featureWrote 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/fivol/claude-make-better/workspace)<a href="https://agentmods.dev/skills/fivol/claude-make-better/workspace"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/workspace/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/fivol/claude-make-better/workspace"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/workspace.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 | $0.00166 | $0.03989 |
| Opus 5 | $0.00083 | $0.01995 |
| Sonnet 5 | $0.00033 | $0.00798 |
| Haiku 4.5 | $0.00017 | $0.00399 |
Grade B, and why
workspace 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 9d 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.
blocking: `gh auth login` (interactive), `proxy-setup.sh` (sudo / binds `:80`), How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace mode — an isolated running copy per task
Overview
Invoked once, this skill puts you into Workspace Mode for the rest of the
session: every task is built in an isolated git-worktree workspace under
<worktrees_dir>/<task>/, and lands in its base branch via a PR. You don't
re-invoke it per step — the conversation drives the phases.
It owns the environment, not the change: worktrees, dependency symlinks,
copied env files, ports, detached dev servers, the proxy, the reaper, the admin
dashboard, and the .feature.json state that ties them together. Delivering the
change is the ship skill; landing it is merge.
When to enter — and when not to
Enter proactively the moment a request in a configured workspace turns into
building/changing/fixing something. Configured means there is a
.claude/feature/config.json at the root — without it, this skill has nothing to
work with and you should not create one just to have it.
Do not enter for:
- read-only questions, code reading, "why does X happen", DB/log inspection, ops;
- a one-off edit the user wants applied where they are, directly on the current branch;
- work the user explicitly wants without a PR ("just commit here", "no PR");
- anything outside the configured repos.
Leaving. "No workspace", "без воркспейса", "just edit here", "stop using the worktree" — that ends Workspace Mode for the session. Say so in one line and work in the checkout the user is in, like any ordinary turn. Re-enter only when they ask for a workspace again. A mode the user cannot leave is a trap, and one request to leave covers the rest of the session, not one message.
If you're already in Workspace Mode this session, stay in it; don't re-enter. On
first entry run the Preflight check below, so a missing tool or an
unauthenticated gh surfaces before you start building.
Core contract: by the time you hand the user a report, the current pass is already simplified, reviewed, committed, pushed and reflected in the PR. The report is the last thing you produce, never the first.
What ships with it
3 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.
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.
- 9d ago First seen · 297 lines · 166 tokens per session scan B f5a7c47772e1
workspace is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 28d ago), licensed MIT. It adds 166 tokens to every session and 3,989 once invoked, about $0.0008 per session on Opus 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…