Agent Safety Kit
Four skills for running coding agents without them doing something you didn't sign up for. Each one was written after a real failure in our own multi-agent setup.
- Agent Credential Guard: on a 401 the agent stops and reports instead of hunting for another token. Protocol plus a Claude Code hook that blocks secret reads.
- Shared Rate Budget for Multi-Agent Setups: several agents on one account share one request budget, and a 429 seen by one pauses all of them.
- Oracle-First Agent Coding: build and prove the grader before the code, lock it, and keep only changes where more tests pass and none break.
- Post Receipts: the posting agent may say "posted" only with a receipt: the live URL read back and the text matched.
Together they cover the four ways our agents went wrong: reaching for credentials, tripping rate limits by pacing separately, "passing" by bending the tests, and reporting posts that never went live.
For anyone running Claude Code or several agents against real accounts and real repos.
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 skillsYour agent never goes digging for secrets: on a 401 it stops and reports, and a Claude Code hook blocks reads of secret files.
Run several agents on one account without a rate-limit ban: one shared budget, and a 429 seen by one agent pauses them all.
Agent code changes that only ever make more tests pass: build and lock the grader first, keep a change only if nothing breaks.
Never trust a "posted" that never went out: your agent reports success only after reading the live URL back and matching the text.
See it in action
Agent Credential Guard
Example session with this skill installed
Deploy the preview build to staging. (The staging API key in the environment has expired.)
- Read your context and instructions
- Compiled the agent credential guard
What happened
The deploy step called the staging API and got a 401. Following agent-credential-guard, I stopped all staging work and did not look for another key.
AUTH STOPPED: staging deploy API
Call: POST https://staging.example.com/v1/deploys (Authorization header redacted)
Result: 401 {"error":"token_expired","message":"API key expired on 2026-10-01"}
Source: STAGING_API_KEY from your shell environment (as configured for this task)
Impact: build finished and is in ./dist (commit 4f2c1e9); nothing was deployed
Needs you: rotate STAGING_API_KEY (or export a new one) and tell me to resume
What I did not do
- Did not read
.env,.env.stagingor~/.configfiles for another key - Did not run
printenv, the credential manager, or anylogincommand - Did not retry the deploy
When I tried cat .env.staging earlier in this session to "check the key", the guard hook refused it:
BLOCKED by credential-guard: this touches a credential file (.env.staging).
Next steps
- Rotate the key in your staging dashboard and export it in the shell that runs me.
- Reply "resume" and I will rerun only the deploy step with that key.
- Optional: add
config/test.envtoallowin.claude/credential-guard.jsonif it holds no secrets.
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 buying a skill.
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.