Agent Foreman Pack — all four skills
All four Agent Foreman skills for AI coding agents: Orchestrator (multi-problem intake, fresh worker per task, handoff), Verify & Repair (independent QA + automatic repair loop), Git Guard (blocks destructive git and file operations) and Token Meter (where your tokens and money go). Save ~25% versus buying separately.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 4 skills unlock instantly in your library.
What's included
4 skillsA safety floor for AI coding agents. Parses real shell syntax and blocks reset --hard, clean, rebase, amend, force push, branch -D, --no-verify, author spoofing, recursive deletes of repo roots and writes outside your project. Rules for any agent plus a PreToolUse hook and a --check CLI.
Turn a messy request into one self-contained task file per problem, keep a ledger so nothing is lost, dispatch each task to a fresh worker (parallel only when write-safe), verify every result independently with automatic repair, and hand off to a fresh session with a ready prompt.
One self-contained Python script that reads your local Claude Code transcripts and shows spend by session, day, model and context size, subagents included and de-duplicated per call, then tells you at what context size to hand off. Optional live budget hook. No network.
Stop trusting "done, all tests pass". A fresh reviewer subagent checks every original acceptance criterion against the real diff and its own test runs, proves new tests fail before the fix, returns PASS/FAIL with re-runnable evidence, and loops failures through repair.
See it in action
Agent Foreman Git Guard - Stop AI Agents Destroying Work
Example session with this skill installed
The tests keep failing, let's start fresh: cd api && git stash && git checkout -- . && git clean -fdx
- Read your context and instructions
- Compiled the agent foreman git
Summary
The agent proposed one tidy "start fresh" line. Foreman Git Guard parsed every step of the chain and refused the tool call before anything ran, so no uncommitted work was lost.
Guard verdict: DENY
| Step in the chain | Verdict | Reason |
|---|---|---|
cd api | allow | plain navigation |
git stash | deny | git stash is blocked (only stash list / stash show): it hides other people's work in a shared tree, and a failed pop loses it |
git checkout -- . | deny | discards uncommitted changes in the working tree |
git clean -fdx | deny | deletes untracked and ignored files, including a colleague's fixtures |
Because one step is denied, the whole command is denied - the tool call never executes.
What the agent does instead
Following the skill's pre-flight rules, the agent:
- Runs
git statusandgit diff --stat(both allowed). - Reports exactly which files it changed in this session.
- Asks you whether to revert only its own edits with a new commit, instead of wiping the tree.
It cannot be wrapped around
| Attempt | Result |
|---|---|
forced push inside bash -c inside $( ... ) | DENY - all three layers parsed |
git commit --no-verify to skip a failing lint hook | DENY - "fix what the hook reports" |
| recursive delete of a folder named by an unresolved variable | DENY - "use a literal path" |
git status, git diff, git push origin feature/x, git checkout -b, deleting node_modules | ALLOW - normal work flows untouched |
Next steps
- In Claude Code, keep the
PreToolUsehook installed so every shell call is checked automatically. - In Cursor or Codex, have the agent run
python foreman_guard.py --check "<command>"first (exit 2 = deny). - Add project-specific protected folders or a commit-subject regex in
.foreman-guard.json.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.