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 skills add dgk-dev/dgk-gpt --skill cpgit clone --depth 1 https://github.com/dgk-dev/dgk-gptWrote 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/dgk-dev/dgk-gpt/cp)<a href="https://agentmods.dev/skills/dgk-dev/dgk-gpt/cp"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/cp/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/dgk-dev/dgk-gpt/cp"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/cp.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 | $0.00075 | $0.00573 |
| Opus 5.5 | $0.00030 | $0.00229 |
| Sonnet 5.5 | $0.00015 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
cp 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cp
Use this as a thin finish mode after implementation is done.
cp is the local gate before push: verify first, then commit and push the intended changes on the current branch.
Default Flow
- Inspect:
git status- current branch
- intended files for this task
- recent commit message style if needed
- Run the closest local verification to the repo's normal safety checks before committing.
- Prefer repo-native commands over invented ones.
- Prefer the narrowest safe checks first: changed-file lint/format checks, affected package tests, or targeted builds.
- If the repo's only reliable gate is broader, run the broader command.
- If a broad local check fails because of unrelated dirty files outside the intended change set, stop and report that clearly instead of fixing or staging those unrelated files.
- Stage only the intended files explicitly.
- If a commit message was not provided, generate a concise conventional commit message that matches the repo style.
- Commit on the current branch.
- Committing directly to
mainormasteris allowed when that is the repo or user's chosen workflow. - If the repo explicitly requires short-lived branches, follow that instead.
- Push the current branch.
- If upstream is missing, push with upstream tracking.
Rules
- Never use
git add .,git add -A, or similar broad staging. - Never commit unrelated local changes from other tasks or sessions.
- Never commit secrets,
.envfiles, credentials, or generated noise by accident. - Never silently skip verification; state what ran and what was skipped.
- Never force push unless the user explicitly asks for it.
- Do not create or require a PR unless the user explicitly asks for one.
Good Targets
- "/cp"
- "커밋하고 푸시해줘"
- "메인에 올려"
- "이제 검증하고 바로 푸시해"
Avoid
- Do not use this for "just commit" or "just push" if the user clearly asked for only one of those actions.
- Do not infer permission to push a different branch than the current one.
- Do not hide skipped or excluded files; mention them briefly if they matter.
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.
- 1mo ago First seen · 62 lines · 75 tokens per session scan A ae504c6b4144
cp is a skill published in the GitHub repository dgk-dev/dgk-gpt (55 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 573 once invoked, about $0.0003 per session on Opus 5.5. 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
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
git-commit
Analyze changes with Git only and auto-generate conventional commit messages with optional emoji; suggests splitting commits when needed, runs local Git hooks by default (use --no-verify to skip).
git-master
MUST USE for ANY git operations: atomic commits, rebase/squash/fixup, and history search (blame, bisect, log -S, reflog). Load it before running git yourself, or pass loadskills=['git-master'] to the task that commits. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, pre-commit framework migration, Starlark git.sandbox checks and unstaged fixes, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or…
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.