Maintaining Agent Context
sentimony/skills/skills/maintaining-agent-contextby sentimony53d0630136d6MIT6 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today
You MUST use this when auditing, improving, restructuring, or maintaining a repository's agent instruction and context architecture - AGENTS.md, CLAUDE.md and its variants, .claude/rules/, the instruction layer of SKILL.md files, or docs linked from them - including reducing always-loaded context cost, finding stale, duplicated, or conflicting instructions, and keeping Claude Code or Codex project memory aligned with the codebase. Not for documentation written for human readers, and not for authoring or revising a skill itself.
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| agents/openai.yaml | 124 B | application/yaml |
| CHANGELOG.md | 7.6 KB | text/markdown |
| LICENSE | 1 KB | text/plain |
| references/assessment-criteria.md | 10 KB | text/markdown |
| references/attribution.md | 1.2 KB | text/markdown |
| references/claude-code-loading.md | 4.9 KB | text/markdown |
| references/codex-loading.md | 5 KB | text/markdown |
| references/restructuring-verification.md | 1.4 KB | text/markdown |
| scripts/test_contract.py | 14.4 KB | text/plain |
| SKILL.md | 17.9 KB | text/markdown |
Source and attribution
Source:sentimony/skillsinskills/maintaining-agent-contextat commit53d0630
License: MIT
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from sentimony/skills
Verification Gate
sentimony
A verification gate that requires fresh, attributable evidence before any claim that work is complete, fixed, ready, or mergeable.
Review Resolution
sentimony
Validates code-review findings against the current tree before fixing, then records dispositions and resolution evidence.
Subagent Plan Dev
sentimony
Orchestrates execution of an existing implementation plan through scoped subagents with controller-owned verification and review gates.
Scope Triage
sentimony
Classifies a software request into direct implementation, light spec, or full design before any code is written.
Tdd
sentimony
Guides a test-first development cycle for one behavior, from a valid failing test to green and refactor.
Review Request
sentimony
Prepares and dispatches an independent code review against requirements, scope and the actual Git diff.
More in AI & Agents
Ppt Template Creator
anthropics
Turns a user's PowerPoint template into a reusable skill that generates branded presentations.
Skill Development
anthropics
Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.
Plugin Structure
anthropics
Guides the structure, manifest, and component layout of Claude Code plugins.
Command Development
anthropics
Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.
Claude Md Improver
anthropics
Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.
Find Skills
vercel-labs
Guides discovery, quality checking and installation of agent skills via the npx skills CLI.