Skip to content
Agentmart
Submit a tool

correct

Use when agents repeat a mistake.

Skill by Camgineer

IndexedMIT
Write a review

Chalk Labs

Need help deploying correct?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/camgineer-correct

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when agents repeat a mistake. Prevent it through architecture, types, or checks before adding instructions.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/correct

What's inside

Skill name
correct
Description
Use when agents repeat a mistake. Prevent it through architecture, types, or checks before adding instructions.
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Correct

The operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't make them.

Assume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.

## 1. Find the mistake classes

Read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. When the **History** capability is available, also read the operator's past corrections through the **recall** skill. Group the mistakes into classes. A class counts once it has happened twice. Done when every class has at least two cited instances, each a commit, a review comment, or a quoted correction.

## 2. Pick the highest level that works

Fix each class at the first level that can stop it. This is the [encode-lessons-in-structure](../principles/encode-lessons-in-structure.md) reference run over the repo's history.

1. **Architecture.** Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.
2. **Types.** Make the bad state impossible to write. If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more of it.
3. **Tests.** Test the behavior at a public seam per the [test-behavior-not-implementation](../principles/test-behavior-not-implementation.md) reference. Fix or delete any test that would still pass if every function it calls returned nothing.
4. **Agent rules.** Write docs or agent rules last, and only for judgment calls. Nothing fails when an agent skips them.

Human review is the fallback when every level fails, never the fix.

## 3. Fix and prove

Fix the most frequent classes now, one commit each. Prove each new check fails on a real past mistake by running it against that commit or a reverted copy of it. Run the same command locally and in CI. An exception goes on the offending line with a reason, an expiry date, and the name of the human who approved it.

## 4. Keep the rule table

Keep a table in the agent instruction file that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, the mistake is a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen.

**Reply:** each class with its evidence, the level you picked, and why a higher level didn't work. Link each check's failing run on the past mistake.

From Camgineer/cstack, MIT.

More from Camgineer/cstack

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 12, 2026 (18 days ago)
Last release
Oct 16, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Camgineer

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get correct running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying correct?

CallGet help
Cite this page

correct skill. Agent Mart. https://agentmart.dev/skills/camgineer-correct (last updated 2026-10-24)