In short:
ak-autoresearchis a router: it checks the installed skill catalog, then hands your iterative goal toak-loop,ak-predict,ak-scenario,ak-securityorak-skill-creator. When no route fits, it looks for an observable check, or makes one pass with the normal workflow. It does not run the code-fixing loop itself.
Disclosure: I maintain AgentKit and have an affiliate relationship with it: the AgentKit link in this post is an affiliate link; buying through it gets you 30% off.
Summary
Use it when you want a measurable result to improve over several rounds but do not know which skill handles it, for example raising coverage, finding edge cases, a security review or tuning a skill. You do not need it when you already know the target skill, or when the work needs only one pass with no number to score it.
flowchart LR
A["Goal to iterate on"] --> B["ak-autoresearch"]
B --> C["ak-loop"]
B --> D["ak-predict"]
B --> E["ak-scenario"]
B --> F["ak-security"]
B --> G["ak-skill-creator"]
B --> H["No route fits: normal fix, no loop"]It revolves around 4 points:
| Point | Question | Example |
|---|---|---|
| Router | Which skill actually does this work? | "Raise coverage" goes to ak-loop, "review vulnerabilities by threat" goes to ak-security. |
| Metric | Which number shows this change is better than the last one? | The coverage percentage the test command prints, or the bundle size in KB. |
| Limit and stop condition | How many rounds at most, and when does it stop? | At most 10 rounds, or stop early when coverage reaches 80%. |
| Keep or revert | Is the last change kept? | Coverage goes up but the build is red, so the guard fails and the code goes back to exactly where it was before that round. |
Each round changes only one thing, so you know for sure which change produced the result. Push, publish and deploy still wait for your approval as usual.
Sample prompt for improving a number:
/ak-autoresearch Raise test coverage of <module name> from the current level to 80%.
Constraints: do not delete or loosen existing tests, the build must be green after every round.
--metric "coverage %" --iterations 10| Flag | What it is for | Since ak |
|---|---|---|
--iterations | Takes a number N as the round count | 2.15.0 |
--metric | Takes the name of a metric | 2.15.0 |
Below is the detailed version: the run flow, 6 situations with prompts, two flags with examples, the change history by ak release, and common pitfalls. The detailed version and the interactive page are for subscribers. Your agent can also search them through the portal's MCP.
Opens when your account has subscriber access
This guide is for subscribers
Once your account has access, the full piece, the interactive visual and the agent call all open.
- Sign in or create a modernEngineer accountReading access belongs to your account email.
- Choose a plan on the pricing page1, 3 or 12 months, paid by VietQR bank transfer. Access opens about a minute after the money arrives.
- Or redeem a Facebook subscriber codePeople supporting the page on Facebook get an activation code by message each month.
Already a subscriber? Sign in to read.
Use this piece in your agent
Get an API keyCopy the text below and paste it into Claude Code, Codex or whichever agent you use. The agent reads the piece and checks it against the repo you have open.
Read "ak-autoresearch: route iterative work to the right skill" on modernEngineer and apply it to this repo.
1. Call the content_get tool of the modernengineer MCP server with locale "en", slug "ak-autoresearch". If the modernengineer MCP server is not connected, stop and walk me through connecting it from https://modernengineer.dev/en/mcp.
2. Summarize the main steps of the piece and point out which apply to this repo.
3. Propose concrete changes and ask me before editing any file.Connect MCP in Claude Code (once)
claude mcp add --transport http modernengineer \
https://api.modernengineer.dev/mcp \
--header "Authorization: Bearer <API key>"Reading the full piece over MCP needs an API key from a subscriber account or one that bought this guide. Without access, the agent only gets the opening.
- Version
- v1.0.0
- Updated
- 22/10/2026
- Licence
- All rights reserved
- Slug
- ak-autoresearch
