agentmods.dev

xcodeinstrumentmcp: Skill for Codex

.codex/skills/parser/SKILL.md

parser is a skill for Codex from eksdev007/xcodeinstrumentmcp. It costs 57 tokens per session (308 once invoked), scanned A, original, MIT.

A set of rules for changing code that parses and normalizes Apple export data, turning raw exports into consistent internal data. It covers trace parsing, ranking inputs, adapters, and schema stability.

In plain words
What is it for?
It is for updating parsers, normalization logic, fixtures, expected outputs, and tests for Apple export data.
Why use it?
It prevents the parser from inventing precision, losing ambiguous data, or mixing data extraction with ranking and presentation.

Skill for Codex

Written for Codex: installed under .codex/.

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 57 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/parser/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 parser

README.md
[![agentmods](https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/parser/github.svg)](https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/parser)
Your own site
<a href="https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/parser"><img src="https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/parser/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 parser

Your own site · 80×15
<a href="https://agentmods.dev/skills/eksdev007/xcodeinstrumentmcp/parser"><img src="https://agentmods.dev/badge/skills/eksdev007/xcodeinstrumentmcp/parser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 308 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 $0.00057 $0.00308
Opus 5.5 $0.00023 $0.00123
Sonnet 5.5 $0.00011 $0.00062
Haiku 4.5 $0.00006 $0.00031

Measured 2mo ago against content hash 47d2369faaaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parser 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/parser/SKILL.md · 39 lines

What it actually says

Parser

Use this skill for parser and normalization work.

Goal

Produce deterministic, bounded, versionable normalized outputs from Apple export data without claiming more precision than the source actually supports.

Rules

  • Prefer deterministic normalization over clever heuristics.
  • Preserve stable keys and stable ordering where the format allows it.
  • Keep raw-source ambiguity visible in the normalized model instead of hiding it.
  • Do not silently discard data unless the spec explicitly says to.
  • Separate parsing from ranking and presentation logic.
  • Keep adapter-specific code out of shared domain types where possible.

Required workflow

  1. Inspect the relevant fixture family before changing parser behavior.
  2. Update or add fixtures in the same change as the parser edit.
  3. Update expected normalized outputs and golden summaries if behavior changes.
  4. Run targeted tests first, then bash scripts/verify.sh.

Precision policy

  • Never fabricate durations, counts, or ownership information.
  • When symbols, threads, or intervals are only partially known, model that uncertainty explicitly.
  • Prefer lossless capture in the IR and lossy reduction only in later stages.

Done criteria

A parser change is not done until fixtures, expected outputs, and tests reflect the new behavior.

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 · 39 lines · 57 tokens per session scan A 47d2369faaaf

Subscribe to this mod's changes

parser is a skill published in the GitHub repository eksdev007/xcodeinstrumentmcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 308 once invoked, about $0.0002 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.

instrumentsiosmcp-serverxcode
Related

parser compared with skills from other repositories

parser next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
parsereksdev007/xcodeinstrumentmcpSkill26mo agoMITA57Codex
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