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/cdskill/qalma/git-commitnpx skills add cdskill/qalma --skill git-commitgit clone --depth 1 https://github.com/cdskill/qalmaWhat 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 | $0.00046 | $0.00943 |
| Opus 5 | $0.00023 | $0.00472 |
| Sonnet 5 | $0.00009 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
git-commit 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit
Create a focused conventional commit from the changes that are already staged.
Every commit in this repository MUST carry a type(scope): description header —
a commit without a scope is invalid here.
Workflow
- Run
git status --shortto understand staged, unstaged, and untracked files. - Run
git diff --stagedand analyze only staged changes. - If nothing is staged, stop and ask the user to stage changes first.
- Pick the
typeand a requiredscopefrom the tables below, based on the staged paths. If the diff legitimately spans several scopes, either split it into separate commits or use the broadest accurate scope (e.g.repo). - Generate a conventional commit message that reflects the staged diff.
- Validate before committing: the subject line MUST match
^(feat|fix|docs|style|refactor|perf|test|build|ci|chore)\([a-z0-9-]+\)!?: .+. If it does not (e.g. the scope is missing), fix the message — never commit without a scope. - Create the commit with
git commitusing the validated multi-line message. - Report the commit hash and message summary.
Commit Format
<type>(<scope>): <description>
[optional body]
[optional footer]
The (<scope>) segment is not optional in this repository.
Types
feat: New featurefix: Bug fixdocs: Documentation changesstyle: Code style or formatting changesrefactor: Code restructuring without behavior changesperf: Performance improvementtest: Adding or modifying testsbuild: Build system, dependencies, or packagingci: CI/CD pipeline changeschore: Maintenance tasks
Scopes (required — pick the most specific match)
| Scope | Use for changes under… |
|---|---|
editor |
libs/editor — the @qalma/editor library |
docs |
apps/docs / apps/docs-e2e — the documentation site |
sandbox |
apps/sandbox / apps/sandbox-e2e — the demo app |
bench |
bench/** — benchmarks (e.g. bundle-size) |
infra |
infra/** — Terraform/OpenTofu, hosting, CDN |
skills |
.agents/skills / .claude/skills |
agents |
.agents agent configuration (non-skill) |
release |
Version bumps and release publishing |
repo |
Repo-wide tooling, root config, or genuinely cross-cutting changes |
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.
- yesterday First seen · 99 lines · 46 tokens per session scan A 1bab41cf1543
git-commit is a skill published in the GitHub repository cdskill/qalma (10 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 943 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
heap-snapshot-analysis
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
tool-rename-deprecation
Ensure renamed built-in tool references preserve backward compatibility. Use when renaming a toolReferenceName, tool set referenceName, or any tool identifier. Run on ANY change to tool registration code. Covers legacyToolReferenceFullNames for tools and legacyFullNames for tool sets.
agent-host-e2e-tests
Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…
fix-errors
Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error messages, and hit/user counts. Covers tracing data flow through call stacks, identifying producers of invalid data vs. consumers that crash, enriching error messages…