gcam

gcam is a skill for Claude Code, Codex, Cursor from AdobeDocs/ff-services-docs. It costs 81 tokens per session (947 once invoked), scanned A, original, Apache-2.0.

A guided Git commit workflow that stages all changes, proposes a commit message, and waits for you to review it before committing.

In plain words
What is it for?
It helps stage a whole project, draft a commit message using the project's rules, edit or approve that message, and either commit or reject it.
Why use it?
It prevents accidental commits and lets you check both the staged files and the message before anything is recorded in Git.

Skill for Claude CodeCodexCursor

Install

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.

agentmods
npx agentmods add skills/adobedocs/ff-services-docs/gcam
Any agent
npx skills add AdobeDocs/ff-services-docs --skill gcam
Clone the repo
git clone --depth 1 https://github.com/AdobeDocs/ff-services-docs

Made for: Claude Code, Codex, Cursor.

Wrote 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.

agentmods badge for gcam

README.md
[![agentmods](https://agentmods.dev/badge/skills/adobedocs/ff-services-docs/gcam.svg)](https://agentmods.dev/skills/adobedocs/ff-services-docs/gcam)
Your own site
<a href="https://agentmods.dev/skills/adobedocs/ff-services-docs/gcam"><img src="https://agentmods.dev/badge/skills/adobedocs/ff-services-docs/gcam.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.00947
Opus 5 $0.00041 $0.00474
Sonnet 5 $0.00016 $0.00189
Haiku 4.5 $0.00008 $0.00095

Measured 5d ago against content hash 987940bbfe25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcam 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 5d 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.

.cursor/skills/gcam/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gcam — Stage all, propose message, review, then commit or reject

When to run

Apply when the user wants staging plus a proposed commit message but no commit until they approve—for example /gcam, “gcam”, “stage all and let me edit the commit message”, or “propose a commit then I’ll choose commit or reject”.

Do not run when the user wants an immediate commit with no review—use the gc skill (/gc) instead.

Steps (first message)

  1. Repo root — Run from the git root (git rev-parse --show-toplevel if needed).

  2. Stage everything — Run:

    git add -A
    
  3. Inspect the staged set — Use git status and git diff --cached / --stat so the draft message matches what is staged.

  4. Draft the commit message using User Rules → Git commit messages (same rules as gc: imperative ~50-character subject, blank line, body bullets with 📖 / ✏️, ~72-character wrap). See .cursor/skills/gc/SKILL.md for the full template and examples.

  5. Present for review — Output the message in a single fenced code block labeled clearly so the user can copy and edit it, for example:

    • Proposed commit message (copy/edit below)
  6. Pause for user decision — Do not run git commit yet. End with a short prompt like:

    • Review the proposed message above. You may reply with an edited full message in a code block if you want changes.
    • Then choose:
      • 1 or commit — Commit using the final message (your edited version if you sent one; otherwise the proposal).
      • 2 or reject — Do not commit. Staged files stay staged unless you ask to unstage.
  7. If nothing is staged after git add -A, say so and stop (same as gc).

Steps (user’s follow-up message)

Interpret the reply:

User intent Action
1, commit, or equivalent and (optional) a full commit message in a code block Commit with that message. If they chose 1 but no new message, use the last proposed message from the previous turn.
2, reject, or equivalent Do not run git commit. Confirm that the commit was skipped. Staged changes remain staged by default.
Edited message only (code block) without 1 or 2 Ask them to reply with 1 (commit with that text) or 2 (reject).
Ask to unstage after reject Run git reset HEAD (or git restore --staged . if appropriate for their Git version/workflow) from repo root and confirm.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 5d ago First seen · 66 lines · 81 tokens per session scan A 987940bbfe25

Subscribe to this mod's changes

gcam is a skill published in the GitHub repository AdobeDocs/ff-services-docs (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 947 once invoked, about $0.0004 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 2026-08-31.