implementation-loop

A workflow skill for carrying a software project through repeated implementation and verification steps until it is ready to ship. It selects unfinished acceptance criteria, makes focused changes, and runs the project’s checks after each meaningful change.

In plain words
What is it for?
Use it for repository-wide implementation work, completing a specification, clearing acceptance criteria, or preparing an open-source release. It expects project instructions, verification scripts, and release checks.
Why use it?
It gives long implementation tasks a repeatable way to choose the next useful change and catch regressions early. It also documents blockers instead of treating incomplete work as finished.

Skill for Claude CodeCodex

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/eksdev007/xcodeinstrumentmcp/implementation-loop
Any agent
npx skills add eksdev007/xcodeinstrumentmcp --skill implementation-loop
Clone the repo
git clone --depth 1 https://github.com/eksdev007/xcodeinstrumentmcp

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 539 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 $0.00072 $0.00539
Opus 5 $0.00036 $0.00269
Sonnet 5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured yesterday against content hash 5e850bfe0a94, 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.

.codex/skills/implementation-loop/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Loop

Use this skill when working through the xcodeinstrumentmcp delivery loop over many changes.

Goal

Move the repository toward a releasable state by selecting the highest-value unfinished work, implementing it in bounded slices, and proving progress with the repo scripts.

Primary workflow

  1. Read AGENTS.md and docs/task-definition.md before making changes.
  2. Inspect docs/acceptance-matrix.json and identify the highest-priority failing or unimplemented acceptance IDs.
  3. Choose the smallest implementation slice that can move one or more important IDs forward.
  4. Before coding, inspect the nearby package boundaries and existing docs so the change stays aligned with the repo architecture.
  5. Implement the slice with minimal, production-oriented changes.
  6. After each meaningful change, run bash scripts/verify.sh.
  7. If verify.sh fails, fix the most relevant failure before expanding scope.
  8. Repeat until the selected acceptance IDs are green or until a clearly documented blocker is found.
  9. Before declaring broad completion, run bash scripts/release_readiness.sh.

Working rules

  • Prefer end-to-end progress over broad speculative scaffolding.
  • Prefer one coherent slice over touching every package lightly.
  • Keep the package boundaries intact: CLI, MCP, core, parsers, domain, signposts, sqlite, shared.
  • Keep outputs deterministic and bounded.
  • Keep privacy-sensitive data local by default.
  • Do not silently change schemas, file formats, or public command behavior; update fixtures, docs, and tests in the same change.
  • Do not mark a checklist item complete without test, fixture, schema, or documented manual evidence.

Prioritization

When multiple items are open, prefer this order unless the prompt says otherwise:

  1. Core type-safe domain model and normalized schemas
  2. Deterministic parser/normalizer behavior backed by fixtures
  3. High-value CLI workflows
  4. MCP tool surface for the same workflows
  5. Persistent database and caching behavior
  6. Signpost scan/plan/apply/revert flows
  7. Docs, polish, and release wiring

Read the full file on GitHub · 51 lines

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 · 51 lines · 72 tokens per session scan A 5e850bfe0a94

Subscribe to this mod's changes

implementation-loop is a skill published in the GitHub repository eksdev007/xcodeinstrumentmcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 539 once invoked, about $0.0004 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

xcode-build-fixer

Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has an approved optimization plan from xcode-build-orchestrator, wants to apply specific build fixes, needs help implementing build setting changes, script phase guards, source-level…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 77 tokens

xcode-build-orchestrator

Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 94 tokens

spm-build-analysis

Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds. Use when a developer suspects packages, plugins, or dependency graph shape are hurting clean or incremental build performance, mentions SPM slowness, package resolution time, build…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 87 tokens

xcode-compilation-analyzer

Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 74 tokens

xcode-build-benchmark

Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped .build-benchmark/ artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 77 tokens

xcode-project-analyzer

Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval gates. Use when a developer wants project-level build analysis, slow incremental builds, guidance on target dependencies, build settings review, run script phase analysis…

AvdLee/Xcode-Build-Optimization-Agent-Skill · 72 tokens