agentmods.dev

xcodeinstrumentmcp: Skill for Codex

.codex/skills/implementation-loop/SKILL.md

implementation-loop is a skill for Codex from eksdev007/xcodeinstrumentmcp. It costs 72 tokens per session (539 once invoked), scanned A, original, MIT.

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 Codex

Written for Codex: installed under .codex/. Also seen: mentions AGENTS.md.

This is eksdev007/xcodeinstrumentmcp's own configuration. It tells Codex how to work on xcodeinstrumentmcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xcodeinstrumentmcp configures →

not rated 2repo 6mo ago A scan 72 tokens original MIT
View source ↗ eksdev007/xcodeinstrumentmcp
Reuse

Borrowing it

Nothing to install: this file belongs to eksdev007/xcodeinstrumentmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/eksdev007/xcodeinstrumentmcp/main/.codex/skills/implementation-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/eksdev007/xcodeinstrumentmcp

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implementation-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/implementation-loop/github.svg)](https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/implementation-loop)
Your own site
<a href="https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/implementation-loop"><img src="https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/implementation-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implementation-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/implementation-loop"><img src="https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/implementation-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00072 $0.00539
Opus 5.5 $0.00029 $0.00216
Sonnet 5.5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 2mo ago against content hash 5e850bfe0a94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo ago.

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. 2mo ago 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 6mo ago), licensed MIT. It adds 72 tokens to every session and 539 once invoked, about $0.0003 per session on Opus 5.5. 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.

Planninginstrumentsiosmcp-serverxcode
Related

implementation-loop compared with skills from other repositories

implementation-loop next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
implementation-loopeksdev007/xcodeinstrumentmcpSkill26mo agoMITA72Codex
xcodebuildmcp-cligetsentry/XcodeBuildMCPSkill6.5k6d agoMITA48Claude Code, Codex
xcodebuildmcpgetsentry/XcodeBuildMCPSkill6.5k6d agoMITA45Claude Code, Codex
xcode-build-fixerAvdLee/Xcode-Build-Optimization-Agent-SkillSkill1.3k1mo agoMITA77Claude Code
xcode-build-orchestratorAvdLee/Xcode-Build-Optimization-Agent-SkillSkill1.3k1mo agoMITA94Claude Code
spm-build-analysisAvdLee/Xcode-Build-Optimization-Agent-SkillSkill1.3k1mo agoMITA87Claude Code
xcode-compilation-analyzerAvdLee/Xcode-Build-Optimization-Agent-SkillSkill1.3k1mo agoMITA74Claude Code