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

agent-context

/agent-context

Use to set up or review project agent instructions

Repository
agnostic-ai ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 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
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

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

What it does and when to use it

Use to set up or review project agent instructions

Original author description

Use to set up or review project agent instructions

How it works

  1. Inventory and review
  2. Edit
  3. Placement
Original SKILL.md headings · 33 lines, 357 words
SKILL.md preview
---
name: agent-context
description: "Use to set up or review project agent instructions"
---

# Agent Context

Review the context that reaches coding agents, then make the requested source changes. Keep a review-only request read-only. Use the project's canonical sources; never edit generated entry points.

## Inventory and review

Read `.agnostic-ai/skills/agent-context/references/context-checklist.md`. Inventory only the requested scope and its dependencies. Inspect repository instructions, contributor guidance, source layout, and validation commands before recommending changes.

Trace generated files to their sources. Report duplication, contradictions, stale commands, broad permissions, and unsupported claims with `path:line` evidence and the smallest useful correction. Preserve user-owned configuration and private material.

When delegation helps, use `agent-context-reviewer` for findings and `agent-config-bootstrapper` for accepted edits. Give each a bounded scope, source paths, ownership, and validation budget. Keep independent edits disjoint and expensive checks with one coordinator. If those roles are unavailable, follow this procedure directly.

## Edit

1. Put shared project context in `.agnostic-ai/AGNOSTIC_AI.md`, stable conventions in `rules/`, procedures in `skills/`, and delegated responsibilities in `agents/`. Check `agnostic-ai.yaml` for source overrides. Use a root native file only when the project has no generated source.
2. Keep root context to project purpose, source of truth, validation routing, and boundaries. Link to existing detailed guidance instead of copying it.
3. Keep each instruction with one owner. Preserve non-obvious safety and compatibility requirements when removing duplication. Read references only when the task needs them.
4. Check referenced files and commands against the repository. Verify target-specific claims from current official documentation only when the recommendation depends on them.
5. Follow the project's validation policy. In this repository, use `go run ./cmd/agnostic-ai validate`, `lint`, `sync`, and `sync --check`; `docs/internal/contributing.md#choose-checks-for-your-change` owns additional checks. Review tracked output changes and keep ignored outputs ignored.

## Placement

| Need | Source |
|---|---|
| Project-wide fact or boundary | Root context or a rule |
| Reusable procedure | Skill |
| Delegated responsibility | Agent |
| Directory-specific convention | Scoped rule |
| Tool-specific difference | Target fence or target override |

Finish with the source files changed, behavior clarified, checks and limits. Confirm that generated guidance matches its sources and that referenced resources remain reachable from each emitted location. A clean sync proves matching output, not useful instructions.
Files in this package (2)
  • SKILL.md 3 KB
  • references/context-checklist.md 1 KB

Versions

RepositoryScoreLicence
This page · chemaclass/agnostic-ai86MIT
shakestzd/htmlgraph100MIT
sarthakrastogi/agent-engineer100MIT

Database snapshot: 13.11.2026 · package version 826584140e06 (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

  • 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.…
  • 100bmad-project-context
    Set up, adopt, refresh, or audit a repository''s agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name
  • 100maintaining-agent-context
    You MUST use this when creating, auditing, optimizing, or maintaining repository agent instructions - AGENTS.md, CLAUDE.md, .claude/rules/, and instruction-related SKILL.md content - covering context architecture, always-loaded context cost, stale, duplicated, or conflicting…
  • 100write-agents-files
    Use when setting up or improving agent instructions in AGENTS.md, CLAUDE.md or other coding agents instructions files.
  • 100init
    This skill should be used when a user asks to initialize a repository for AI agents, create or update an AGENTS.md file, scaffold agent instructions for a codebase, or improve existing agent guidance. Triggers include phrases like 'create an AGENTS.md', 'set up agent…
  • 90gds-generate-project-context
    Create optimized project-context.md for AI agent consistency. Use when the user says "project context" or "generate context

Feedback and reports

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