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/samzong/gmc/gmcnpx skills add samzong/gmc --skill gmcgit clone --depth 1 https://github.com/samzong/gmcWrote 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/samzong/gmc/gmc)<a href="https://agentmods.dev/skills/samzong/gmc/gmc"><img src="https://agentmods.dev/badge/skills/samzong/gmc/gmc.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.01278 |
| Opus 5 | $0.00062 | $0.00639 |
| Sonnet 5 | $0.00025 | $0.00256 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
gmc 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IRON LAW: ALL WORKTREE OPERATIONS MUST USE gmc wt <subcommand>. NEVER INVENT gmc add, gmc rm, gmc prune, gmc clone, OR OTHER TOP-LEVEL WORKTREE COMMANDS.
gmc
Use $ARGUMENTS and the user's words to route into exactly one mode.
Copy this checklist and check off items as you complete them:
- Step 0: Parse intent [BLOCKING]
- Classify the request as
commit,wt add,wt prune,wt share,wt sync,wt rm,wt ls,wt dup,wt pr-review, ortag - If the intent is unclear, ask one focused question before running commands
- Classify the request as
- Step 1: Validate context [BLOCKING]
- Confirm
gmcexists - Confirm the current directory is a git repo when the command needs repo context
- If the action depends on GitHub state, confirm
ghworks first
- Confirm
- Step 2: Preview plan [REQUIRED]
- Show the exact command you plan to run
- For destructive or bulk actions, prefer
--dry-runfirst
- Step 3: Execute exactly one workflow
-
commit -
wt add -
wt prune -
wt share - other
gmc wtsubcommand ortag
-
- Step 4: Report result
- State the exact command run
- Report the created path, cleaned worktrees, synced resources, or generated message
- State what was not run
Routing
commituses top-levelgmc- Any worktree action uses
gmc wt <subcommand> - If the user says
gmc add, translate it togmc wt addand say so - If the user wants generic git help without
gmc, do not use this skill
Common commands
gmcgmc -ygmc -a -ygmc -a -y -p "context"gmc --dry-rungmc wt add <name>gmc wt add <name> --syncgmc wt add <name> -b <branch>gmc wt lsgmc wt rm <name>gmc wt rm -D <name>gmc wt prunegmc wt syncgmc wt share lsgmc wt share add <path> --strategy copygmc wt share add <path> --strategy linkgmc wt share syncgmc tag
Workflow: commit mode
- Use top-level
gmc, notgmc wt - Default to interactive
gmcunless the user explicitly wants automation - Ask before
gmc -a -ybecause it stages all files and auto-confirms - Use
gmc --dry-runwhen the user wants a suggested message without committing
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.
- 4d ago First seen · 115 lines · 123 tokens per session scan A 8438f608f98b
gmc is a skill published in the GitHub repository samzong/gmc (18 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,278 once invoked, about $0.0006 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
ship
Commit and push the current work properly — lint, run the release gate, write a detailed commit message, push to GitHub. Use whenever work reaches a milestone or the user says ship it, commit, or push.
commit-message
Guide for writing clear, consistent git commit messages following this repository's conventions.
commit
Generate git commit messages from staged changes.
quantmind-dev
Contributor workflow for the QuantMind codebase. Covers contributor setup (environment + hooks), filing issues, commit format, pull request format, and component development across quantmind/ modules (etl, knowledge, configs, preprocess, rag, flows, mind, utils) with tests, examples, and verification. Use when setting…
commit
Smart commit: bump version, find related issues, commit with Co-authored-by, push. Use when the user says 'commit' or wants to finalize changes.
commit
Analyze changes, write a conventional commit, and (when shipping) open a PR with closing keywords so referenced issues auto-close on merge. Use when the user asks to commit, push, or open a PR.