Skip to content

Skills / implement

implement

Carry out an agreed plan in small steps, checking each one before the next. Use after a plan is approved, or when asked to build or change something with clear requirements. Do not use when the requirements are still unclear; plan or ask first.

OfficialAuditB
Latest
v1.1.0
Aisle
code
Works with
Claude Code, Codex, Cursor
Stars
2

Install

Install implement

npx @agentsaisle/cli add implement

Installs into your project's skills folder. Add --global to install it for every project.

Audit

B
Critical
0
High
0
Medium
1
Low
0

3 files · audited 2026-10-29 · rules 1.0.0

MediumAA-P02Can write files and run interpreters without disable-model-invocation

SKILL.md:6

Read Grep Glob Edit Write Bash(git diff *) Bash(git status *) Bash(node *) Bash(npm run *) Bash(pnpm *) Bash(yarn *) Bash(bun *)

Why The agent may load this skill on its own and then write files and run code in one go.

Fix Set disable-model-invocation: true so the user starts it, or narrow the Bash patterns.

What this skill can use

Tools

  • Read
  • Grep
  • Glob
  • Edit
  • Write
  • Bash(git diff *)
  • Bash(git status *)
  • Bash(node *)
  • Bash(npm run *)
  • Bash(pnpm *)
  • Bash(yarn *)
  • Bash(bun *)

Scripts

None

Domains mentioned

None

Automated checks found the patterns listed here. An audit reduces risk; it is not a guarantee of safety. How audits work · Read the rules

Show this grade in a README

The badge updates when the registry is rebuilt. Paste this Markdown into the README:

[![aisle audit](https://img.shields.io/endpoint?url=https%3A%2F%2Fagentsaisle-vercel.vercel.app%2Fbadges%2Fimplement.json)](https://agentsaisle-vercel.vercel.app/skills/implement)

SKILL.md

Rendered from commit 4036c95

Implement

Use when

  • A plan is approved and it is time to build.
  • The user gives a change with clear requirements.

Don't use when

  • The requirements are unclear or conflict. Plan first or ask.
  • The change is a review, an explanation or a question.

Steps

  1. Take the next step only. Make the smallest change that completes it.
  2. Match the surrounding code: naming, structure, comment density, error handling. Do not introduce a second way to do something.
  3. Run the checks for that step (tests, type check, lint) before moving on. If one fails, fix it now; never stack changes on a broken step.
  4. Add or update tests alongside the code, not at the end.
  5. If the code shows the plan is wrong, stop, say what you found and propose a change. Do not work around it quietly.
  6. After the last step, summarize what changed, what you ran and what is left for the user to decide.

Budget

  • Search first (grep, glob, symbol search). Read line ranges, not whole files.
  • Read at most 8 files per step. If you need more, write down what you learned and narrow the question.
  • Do not re-read a file you just wrote or edited.
  • Prefer the smallest command output that answers the question: head, tail, quiet flags, filtered lists.
  • Do not add features, refactors or dependencies the plan did not ask for.

Output

  • The changed files, the checks you ran with their results, and anything left open.

Done when

  • Every plan step is done and its check passes.
  • Tests cover the new behavior.
  • Nothing outside the plan was changed.

Version history

VersionCommitInstall
1.1.0latest4036c95add implement

Report this skillAgent Aisle on GitHub