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/outlinedriven/odin-claude-plugin/commit-pushnpx skills add OutlineDriven/odin-claude-plugin --skill commit-pushgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWhat 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 | $0.00017 | $0.00927 |
| Opus 5 | $0.00009 | $0.00464 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
commit-push 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git commit and push
Asking the user: use the platform's blocking question tool -- AskUserQuestion in Claude Code (ToolSearch with select:AskUserQuestion first if unloaded), request_user_input in Codex, ask_question in Antigravity (agy), ask_user in Pi (pi-ask-user extension). Fall back to chat only when no blocking tool exists or the call errors, not for an unloaded schema. Never skip the question silently.
Context
On platforms other than Claude Code, run the Context fallback below. In Claude Code, the labeled sections contain pre-populated data. Use them directly.
Git status:
!git status
Working tree diff:
!git diff HEAD
Current branch:
!git branch --show-current
Recent commits:
!git log --oneline -10
Remote default branch:
!git rev-parse --abbrev-ref origin/HEAD 2>/dev/null || echo 'DEFAULT_BRANCH_UNRESOLVED'
Context fallback
printf '=== STATUS ===\n'; git status; printf '\n=== DIFF ===\n'; git diff HEAD; printf '\n=== BRANCH ===\n'; git branch --show-current; printf '\n=== LOG ===\n'; git log --oneline -10; printf '\n=== DEFAULT_BRANCH ===\n'; git rev-parse --abbrev-ref origin/HEAD 2>/dev/null || echo 'DEFAULT_BRANCH_UNRESOLVED'
Step 1: Resolve branch state
The remote default branch returns something like origin/main; strip the origin/ prefix. If it returned DEFAULT_BRANCH_UNRESOLVED or bare HEAD, try gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'. If both fail, fall back to main.
- Detached HEAD: ask whether to create a feature branch (derive name from change content if yes). If no, stop.
- On default branch with work (uncommitted, unpushed, or no upstream): auto-create a feature branch (pushing default directly isn't supported), derive name from change content, continue at Step 3. Don't ask -- committing on default isn't an option here.
- On default branch, no work: report nothing to do and stop.
- Feature branch: continue.
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.
- 2d ago First seen · 71 lines · 17 tokens per session scan A b5088ec1137e
commit-push is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 6d ago), licensed Apache-2.0. It adds 17 tokens to every session and 927 once invoked, about $0.0001 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
respond-action
Use when screened review findings should be fixed on the current branch, usually as one verified commit per finding.
commit
Create a git commit following project conventions.
git-branch-soft-reset-and-recommit
Use when commit history must be rebuilt into atomic reviewable commits while preserving the branch's final tree and authorship.
pr-merge-commit
Generate a gold-standard merge commit message from branch diff.
lean-writing
Use when commit messages or prose must stay tight: cut filler, padding, preamble, AI fluff, and stories of attempts; lead with current results.
cass
Mine past agent sessions for working prompts, decisions, and patterns (session archaeology). Triggers: "cass", "mine past agent sessions for", "cass skill".