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 commands/fprochazka/claude-code-plugins/commit-allgit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00011 | $0.00631 |
| Opus 5 | $0.00005 | $0.00316 |
| Sonnet 5 | $0.00002 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
commit-all scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current branch: !
git branch --show-current
Git status
!`git status`
Recent commits
!`git log -n 10 --oneline --abbrev-commit`
Changed files (staged and unstaged)
!`git diff HEAD --numstat`
Commits on this branch since it diverged from the base branch (fixup candidates)
Pushed or not, these stay rewritable until the branch merges.
!`base=$(git symbolic-ref -q --short refs/remotes/origin/HEAD 2>/dev/null); base=${base:-$(git rev-parse -q --verify master >/dev/null 2>&1 && echo master || echo main)}; git log --oneline "$base..HEAD" 2>/dev/null; [ -n "$(git log --oneline "$base..HEAD" 2>/dev/null)" ] || echo "(none — HEAD is at or behind $base)"`
Files touched by those commits
!`base=$(git symbolic-ref -q --short refs/remotes/origin/HEAD 2>/dev/null); base=${base:-$(git rev-parse -q --verify master >/dev/null 2>&1 && echo master || echo main)}; git diff --name-only "$base...HEAD" 2>/dev/null | sort -u`
Your task
Load the git-workflow skill and commit all pending changes (both staged and unstaged) according to its rules. Read file diffs as needed via git diff HEAD -- <path> before staging.
Work in this order:
- Check for fixups first. For each pending change ask: would one of the branch commits above have looked different if you had known this at the time? If yes it belongs inside that commit —
git commit --fixup <sha>, not a new commit. Repairing, simplifying or rearranging code this branch introduced is a fixup. Adding new work on top of a commit that was correct as written is not, even when it touches the same files. - Apply the sibling/ancestor test to whatever remains. Ancestors — pieces that only exist because the next one needs them — are one commit, cut vertically through every layer. Siblings — independent, revertible in any order, each meaningful to someone reading
masterwho never saw this branch — stay separate. - Order by dependency: quarantined noise and standalone prerequisites first, payload next, unlocked cleanups and docs last.
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 · 56 lines · 11 tokens per session scan A 683c6bf77f52
commit-all is a command published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 631 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.