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.
git clone --depth 1 https://github.com/pleaseai/claude-code-pluginsWrote 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/commands/pleaseai/claude-code-plugins/modify)<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/modify"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/modify/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/commands/pleaseai/claude-code-plugins/modify"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/modify.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 | $0.00020 | $0.00588 |
| Opus 5 | $0.00010 | $0.00294 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
modify 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply working-tree changes to the current branch and automatically restack every upstack descendant. User input: $ARGUMENTS.
Modes
- Amend (default) — folds staged changes into the existing commit. PR keeps the same identity; force-push needed on next submit.
gt modify -a # stage all + amend gt modify # amend already-staged changes - New commit — adds a new commit on the same branch.
Always passgt modify -cam "fix tests" # stage all + new commit with message gt modify -cm "fix tests" # already-staged changes + new commit with message-m "<message>"—gt modify -calone opens$EDITORfor the message, which hangs in a non-interactive shell. - Into a downstack branch — amend changes into an ancestor branch, then restack upward.
gt modify --into <ancestor-branch>
Steps
- Run
git status --shortandgt lsso the user sees what is staged and where it will land. - Pick the mode from
$ARGUMENTS. If ambiguous (multi-commit branch already exists), ask the user: amend or new commit? Amend keeps the branch single-commit (preferred Graphite style); new commit makes it a multi-commit branch that may needgt squashlater. - Run the chosen
gt modifycommand. - If the auto-restack hits conflicts:
- Resolve in the editor.
gt add .to mark resolved.gt continue -ato finish the restack chain.gt abortto back out cleanly.
- Run
gt lsto confirm the new state.
Key flags
-a, --all— stage all modified files before amending-c, --commit— create a new commit instead of amending-m, --message <msg>— commit message (for-cor to reword on amend)-p, --patch— interactive hunk staging--into <branch>— amend into a downstack branch in one step
When to use gt absorb instead
If the working-tree changes belong to multiple downstack branches (e.g. you fixed several bugs across the stack), use gt absorb -a — Graphite picks the right branch per hunk.
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 · 50 lines · 20 tokens per session scan A e573878d9129
modify is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 588 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 2026-09-07.
Other commands, from other repositories
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
feat
Quick feature commit. Use for new feature, add feature, implement, create new.
step6-ship
Pipeline Step 6 — Ship the completed phase: commit, update roadmap, capture postmortem, optionally push and create PR.