Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/paulnsorensen/easy-cheesenpx agentmods add skills/paulnsorensen/easy-cheese/meltWrote 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/paulnsorensen/easy-cheese/melt)<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/melt"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/melt/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/paulnsorensen/easy-cheese/melt"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/melt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 82 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00104 | $0.02371 |
| Opus 5 | $0.00052 | $0.01185 |
| Sonnet 5 | $0.00021 | $0.00474 |
| Haiku 4.5 | $0.00010 | $0.00237 |
Grade A, and why
melt 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 4d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/melt
Use this skill to resolve Git conflicts with this cascade: mergiraf → rerere → kdiff3. Each stage handles conflicts that remain after the prior stage.
File IO routing
Use the selected source-code backend for conflict searches, bounded reads, and manual edits.
Follow the route in code-intelligence-routing.md.
Use this sequence for manual resolutions: search, fresh bounded read, stale-safe write.
Cascade
| Stage | Tool | Purpose | Start condition |
|---|---|---|---|
| 1 | mergiraf |
Merges syntax trees and preserves independent additions. It uses text merge after a parse failure. | Git starts it as a merge driver, or the user runs batch-resolve. |
| 2 | git rerere |
Reuses a recorded human resolution for the same conflict signature. | Run it after mergiraf when rerere.enabled is true. |
| 3 | kdiff3 |
Provides a manual three-way diff for unresolved conflicts. | Start it with git mergetool --tool=kdiff3. |
Protocol
0. Check for squash residue
Run this check before the conflict summary.
python3 skills/melt/scripts/melt.pyz detect-squash-residue
If the verdict is SQUASH-MERGED, stop the cascade.
Show both printed remedies to the user without changes.
Do not apply either remedy automatically.
The user selects and copies one remedy.
Flags:
--base— Sets the base ref. The default isorigin/main.--branch— Sets the branch. The default is the current branch.--json— Produces structured output.
The detector checks these signals in order:
tree-match— Searches base commits for a tree that matches a branch point. A match identifies the equivalent squash point. This check works offline and supports fork PRs, renames, and later branch commits.gh-api— Runs withtree-match. It adds the PR number, URL, and merge commit when its commit data matches. It can provide the verdict whentree-matchfinds no match.local-synth— Creates a possible squash commit from theHEADtree. It usesgit cherryto find an equivalent commit on the base. It runs only when the other signals provide no verdict. It cannot separate squashed commits from unique commits.
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.
- 4d ago Changed · +105 lines · -79 tokens per session 9e0c37507e5f
- 10d ago First seen · 172 lines · 183 tokens per session scan A 370238fe02f6
melt is a skill published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 2,371 once invoked, about $0.0005 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
ring:committing-changes
Commit changes with scope allowlist enforcement, atomic grouping, GPG-signed conventional commits, and trailer management. Detects the repo's PR-validation scope policy before proposing any message. Use when the user asks to commit or has changes ready to record. Skip when the working tree is clean or the user wants…
ring:opening-pull-requests
Open a GitHub Pull Request with automatic base branch detection, scope allowlist enforcement, PR template filling, and post-create base verification. Replaces ring:generating-pr-descriptions. Use after pushing a branch when ready to open a PR. Skip if the branch is not yet pushed or there are uncommitted changes …