implementation-loop

A repeatable method for making a code change: understand the goal, plan the work, build the smallest complete solution, and verify it.

In plain words
What is it for?
Use it when adding a feature or changing existing behavior, especially when multiple files are involved. It covers acceptance criteria, codebase review, planning, implementation, tests, and manual checks.
Why use it?
It reduces the risk of coding against a misunderstanding or leaving a change untested. It also keeps edits focused on the requested feature or behavior.

Skill for Claude CodeCodexCursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/kingemma7/cursor-os/implementation-loop
Any agent
npx skills add KingEmma7/cursor-os --skill implementation-loop
Clone the repo
git clone --depth 1 https://github.com/KingEmma7/cursor-os

Made for: Claude Code, Codex, Cursor.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00381
Opus 5 $0.00016 $0.00191
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured yesterday against content hash 9c80de9657eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

template/.cursor/skills/implementation-loop/SKILL.md · 36 lines

What it actually says

Implementation Loop

A repeatable loop for shipping a change that actually works and fits the codebase. Follow the phases in order; don't skip to coding.

1. Understand

  • Restate the goal as explicit acceptance criteria. If the request is vague, ask or state your assumption.
  • Read the relevant code, AGENTS.md, and docs/ (architecture, repo-memory, decision-log) before designing. Match existing patterns.
  • Surface conflicts with the current codebase now, not after building.

2. Plan

  • For multi-file or risky work, write a short plan: files to touch, the approach, and the verification you'll run.
  • Choose the smallest complete solution. Reuse existing utilities and patterns before adding abstractions or dependencies.

3. Build

  • Make surgical changes scoped to the goal. Don't refactor unrelated code in the same pass.
  • Keep each modified file traceable to the request. Note unrelated issues separately instead of fixing them inline.

4. Verify

  • Run the project's checks: types, lint, tests, and a manual check of the actual behavior. Don't assume — run them.
  • Compare the result against docs/quality-rubric.md. Cover edge cases, error states, and the failure modes the change introduces.
  • If checks cannot be run, explain exactly why and provide the safest manual verification path.

5. Report

  • State what changed and why, how you verified it (commands and results), and any remaining risks or follow-ups.
  • Update project memory: record durable facts in docs/repo-memory.md and append notable decisions to docs/decision-log.md.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 36 lines · 33 tokens per session scan A 9c80de9657eb

Subscribe to this mod's changes

implementation-loop is a skill published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 20d ago), licensed MIT. It adds 33 tokens to every session and 381 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

onboard-repository

Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…

hoangnb24/repository-harness · 87 tokens

audit-onboarding-proposal

Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…

hoangnb24/repository-harness · 104 tokens

improve-harness

Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…

hoangnb24/repository-harness · 76 tokens

engineering-wisdom

Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…

hoangnb24/repository-harness · 78 tokens

encode-invariant

Convert accepted repository rules into the smallest repository-native mechanical validation with positive and negative proof and precise enforcement-level reporting. Use for requests to enforce architecture, reliability, security, or quality boundaries; prevent a documented violation from recurring; add structural…

hoangnb24/repository-harness · 81 tokens

daily-brief

Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.

craigcossairt/trellis · 60 tokens