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/merge)<a href="https://agentmods.dev/skills/fivol/claude-make-better/merge"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/merge/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/merge"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/merge.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 | $0.00112 | $0.03090 |
| Opus 5 | $0.00056 | $0.01545 |
| Sonnet 5 | $0.00022 | $0.00618 |
| Haiku 4.5 | $0.00011 | $0.00309 |
Grade C, and why
merge scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$ROOT/<worktrees>/<task>" # leftover .feature.json / empty repo dirs How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge — integrate the task branch, then clean up
Runs only on an explicit user go-ahead ("done", "finish", "merge it", or the
equivalent in the user's language). Confirm once before merging. In workspace
context read <worktrees>/<task>/.feature.json for the repos, base branches,
ports, PIDs and PR links, and do every step for all involved repos;
standalone, the current repo and its branch's PR are the whole job (steps 7–9
are then no-ops).
Strategy — read it from the config, don't assume:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/config.py" --root "$ROOT" # → .merge
merge.strategy |
merge.via |
What happens |
|---|---|---|
merge (default) |
local-push |
Merge the task branch into BASE locally and push. The task SHAs land in BASE, so the host marks the PR Merged by itself and your local base is already up to date. |
merge |
gh |
Same commit shape, but the host performs it (gh pr merge --merge); pull BASE afterwards. |
squash / rebase |
gh (forced) |
The host rewrites the SHAs (gh pr merge --squash|--rebase). Required by repos with a squash-only policy. Steps 5–6 below are replaced by that single call, and the local base is refreshed with git pull --ff-only. |
Whatever the strategy, step 2 is not optional: the integration happens on the
task branch, in its worktree, so the PR shows exactly what will land and CI runs
on it. merge.wait_ci: false skips step 3; merge.cleanup: false stops after
step 6.
Per repo: WT="$ROOT/<worktrees>/<task>/<repo>", BRANCH = the task branch,
BASE = .feature.json .repos.<repo>.base (the repo's base_branch).
ROOT = the workspace root — anchor it via the .claude/feature/config.json
marker, never $(pwd). SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts".
1. Make sure the task branch is fully committed
git -C "$WT" status --porcelain # must be empty
2. Sync the latest base into the task branch — resolve conflicts HERE (in the worktree)
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.
- 10d ago First seen · 224 lines · 112 tokens per session scan C a7c61edb586d
merge is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 29d ago), licensed MIT. It adds 112 tokens to every session and 3,090 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.