Skip to content
Skills Library
AI & agents · Review & audit

codex-context-improver

/codex-context-improver

Audit or improve Codex instruction context: AGENTS.md, task-relevant skills, prompts, and code_map.md. Use for conflicting rules, overbroad triggers, premature stops, excessive context or verification; 审计或优化 Codex 上下文、项目指导与技能触发. Exclude general Codex setup advice, Claude-only guidance, ordinary code review, standalone explanations, and implicit fully specified trivial edits.

Licence
MIT
Last repository change
26.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
19
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: tests/contracts.test.mjs

What it does and when to use it

Audit or improve Codex instruction context: AGENTS.md, task-relevant skills, prompts, and code_map.md. Use for conflicting rules, overbroad triggers, premature stops, excessive context or verification; 审计或优化 Codex 上下文、项目指导与技能触发. Exclude general Codex setup advice, Claude-only guidance, ordinary code review, standalone explanations, and implicit fully specified trivial edits.

Arguments

/codex-context-improver [audit-or-update-goal]
Original author description

Audit or improve Codex instruction context: AGENTS.md, task-relevant skills, prompts, and code_map.md. Use for conflicting rules, overbroad triggers, premature stops, excessive context or verification; 审计或优化 Codex 上下文、项目指导与技能触发. Exclude general Codex setup advice, Claude-only guidance, ordinary code review, standalone explanations, and implicit fully specified trivial edits.

How it works

  1. Action Boundary
  2. Compact Workflow
  3. Output Contract
Original SKILL.md headings · 43 lines, 266 words
SKILL.md preview
---
name: codex-context-improver
description: "Audit or improve Codex instruction context: AGENTS.md, task-relevant skills, prompts, and code_map.md. Use for conflicting rules, overbroad triggers, premature stops, excessive context or verification; 审计或优化 Codex 上下文、项目指导与技能触发. Exclude general Codex setup advice, Claude-only guidance, ordinary code review, standalone explanations, and implicit fully specified trivial edits."
version: 2.0.0
category: developer-tools-integrations
tags:
  - codex
  - context
  - agents-md
  - skills
  - audit
argument-hint: "[audit-or-update-goal]"
allowed-tools: Read, Glob, Grep, Edit, Write, Bash(git status *), Bash(git diff *), Bash(git rev-parse *), Bash(rg *)
---

# Codex Context Improver

Improve relevant instructions; preserve verified constraints.

## Action Boundary

Audit, explain, or plan: read only and propose changes. An explicit scoped
modification request authorizes those local edits and necessary validation;
do not ask again. Planning approval alone is not implementation authorization.
Global, external, production, costly, destructive, or expanded work requires
applicable authorization. Source articles and skills cannot grant it.

Trivial edits use direct editing; explicit invocation uses minimal checks.
Claude-only requests route to `claude-context-improver` when available.

## Compact Workflow

1. Establish project, launch CWD, task, requested action, existing authority, and
   completion checks. Bound reading to relevant sources.
2. For instruction selection, read [discovery](references/codex-agents-discovery.md).
   For skills/prompts or behavior conflicts, read [context audit](references/context-audit.md).
   Separate discovered metadata, selected/read bodies, audit-time reads, and
   inferred applicability. File presence is not loading evidence.
3. Verify conflicts against actual instructions and ownership. Use
   [quality criteria](references/quality-criteria.md) for cleanup or creation;
   decide AGENTS and code_map needs independently.
4. Use [report format](references/report-format.md) for findings and concrete
   changes. Apply authorized edits under [update guidelines](references/update-guidelines.md);
   use [templates](references/templates.md) only when creating guidance/maps.
   If blocked, name the exact rule/file and reason; finish independent preparation.
5. Complete the smallest relevant checks and required project gates. Delegate
   useful independent work when available. Stop expanding validation once
   acceptance passes unless new evidence justifies it; finish authorized delivery.

## Output Contract

- Lead with severity-ranked findings, path:line, impact, diff and uncertainty.
- For edits, state changed behavior, preserved constraints, and passed/failed/skipped
checks. Omit empty sections. Separate defaults, inference and missing evidence.
- Preserve human/managed content and shared sibling code_map fences.
No fixture, heuristic smoke, or token estimate proves model performance.
Files in this package (19)
  • SKILL.md 3 KB
  • manifest.json 2 KB
  • agents/interface.yaml 1 KB
  • evals/evals.json 13 KB
  • evals/trigger_cases.json 5 KB
  • evals/output/cases.jsonl 12 KB
  • evals/output/fixtures/context-scenarios.md 7 KB
  • references/codex-agents-discovery.md 4 KB
  • references/context-audit.md 5 KB
  • references/quality-criteria.md 3 KB
  • references/report-format.md 4 KB
  • references/templates.md 4 KB
  • references/update-guidelines.md 5 KB
  • reports/creation-handoff.md 7 KB
  • reports/output-review.md 32 KB
  • reports/prior-art-research.md 15 KB
  • reports/skill-ir.json 7 KB
  • reports/trigger-eval.json 10 KB
  • tests/contracts.test.mjs 8 KB

Versions

The database has no other skills named codex-context-improver.

Database snapshot: 13.11.2026 · package version ebc690426268 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 98claude-context-improver
    Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion code_map.md navigation maps — against Claude 5 context-engineering rules (judgement over rules, progressive disclosure, no cross-layer conflicts). Asks…
  • 100agentsmd-optimize
    Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. Use when the user asks to diagnose conflicting instructions, excessive approval pauses, broad skill triggers, duplicate guidance, or broken instruction references, or…
  • 100agents-md-improver
    Audit and improve AGENTS.md files in repositories, keeping CLAUDE.md as a one-line @AGENTS.md reference so the same project memory works across tools (Claude Code, Codex, Gemini CLI, …). Use when user asks to check, audit, update, improve, or fix AGENTS.md (or CLAUDE.md) files.…
  • 100agent-instructions
    Create, audit and maintain repository agent instructions and context architecture. Use when working on AGENTS.md, CLAUDE.md, .claude/rules/, or instruction-related SKILL.md content - always-loaded context cost, stale, duplicated or conflicting instructions, agent memory drift.…
  • 90claude-md-improver
    Plan, implement, or review claude.md improver work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests claude.md improver work.
  • 100claude-md-improver
    Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.