agent-forge Complete: All 15 Pro Agent Tools
Every paid agent-forge skill in one purchase: the guardrails, the debugging and testing tools, the web design and SEO tools, and the multi-agent pipeline. $242 bought one by one.
Guardrails: Proof-of-Done hooks, Safety Guard, Fake Package Blocker, Memory Saver.
Debug & test: Smart Test Runner, Flaky Test Finder, Log Analyzer, Performance Regression Detector, Diff Coverage Checker, Safe Database Migration Checker.
Web & SEO: Landing Page Designer, Website Design Auditor, GEO + SEO Audit Crawler.
Pipeline: Claude Code Multi-Agent Pipeline (spec to verified build) and the Payments Ledger Test Suite.
Each skill ships its own tool (readable Python, standard library, local, no telemetry) plus the instructions that tell your agent when to run it and how to act on the result. Benchmarks on real open-source repos are on each listing. Works in Claude Code, Cursor, Codex CLI, Copilot and any SKILL.md agent.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 15 skills unlock instantly in your library.
What's included
15 skillsYour agent can't end its turn until the tests ran green after its last edit. Also catches deleted, skipped and weakened tests.
Turn /compact from a reset into a checkpoint: your rules, goal, edited files and last test result are saved before compaction and put back after it.
Five role-restricted sub-agents, from planner to verifier. Hand-offs pass only when a command's exit code says so, never an agent's word.
Turn rm -rf, git reset --hard and force pushes into a checked step: blocks destructive shell commands only when they would really lose work.
Turn any coverage report into the only number that matters for a PR: which changed lines no test runs, grouped by file, with a CI gate.
Turn every pip/npm/cargo install your agent runs into a checked one: blocks typosquats and hallucinated package names before they reach your machine.
Turn a flaky test into a named culprit: measures its failure rate and bisects test order to find the polluting test in a handful of runs.
Turn any website into a scored GEO + SEO fix list: a real crawler checks 69 rules for Google and AI search (ChatGPT, Perplexity, Claude) and writes the fix files.
Turn a one-line brief into a responsive landing page with a real design system, then check it in light and dark mode at three widths until nothing is broken.
Turn a huge log file into a 2 KB summary with the real error on top: templates, counts, folded stack traces and what is new since the last good run.
Drop-in tests for any double-entry ledger: idempotency, concurrency, overdraft races and crash safety, proven against real databases.
Turn 'feels slower' into a verdict: runs old and new code alternately, then reports the slowdown with a confidence interval, or says the noise is too high.
Turn a risky Postgres or MySQL migration into a safe one: flags table locks and rewrites before they hit production and suggests the zero-downtime version.
Turn a slow test suite into just the tests your change can break: maps your git diff to the affected tests and prints the exact command to run.
Turn a rough AI-built page into a polished one: renders it at phone, tablet and desktop, scores the design 0-100 and hands your agent a ranked fix list with annotated screenshots.
See it in action
Claude Code Hooks: Block "Done" Until Tests Really Pass
Example session with this skill installed
Change greet() to return "Hello, <name>!". Just make the edit and tell me it's done; you don't need to run anything.
- Read your context and instructions
- Compiled the claude code hooks
Edit made, but Proof-of-Done blocked the end of the turn:
you changed app/greet.py and no test command has run since your last change. Run
python -m pytest(without piping it into tail/grep), read the result, and only then report.
$ python -m pytest
F
FAILED tests/test_greet.py::test_greet - AssertionError: assert 'Hello, Ada!' == 'Hi Ada'
1 failed
The existing test still asserts the old greeting. I updated it to the behaviour you asked for and re-ran:
$ python -m pytest
.
1 passed in 1.72s
Done. greet() returns "Hello, <name>!".
Evidence: python -m pytest → exit 0, "1 passed", after the last edit.
(Real Claude Code session with Proof-of-Done installed, trimmed.)
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.