agent-context-bootstrap

agent-context-bootstrap is a skill for Claude Code, Codex from stark-ai-de/agent-skills. It costs 54 tokens per session (1,242 once invoked), scanned A, original, Apache-2.0.

A setup process that adds repository-specific instructions for coding agents such as Codex, Claude Code, or Cursor. These instructions describe the project's commands, documents, terminology, rules, and validation steps.

In plain words
What is it for?
Use it to create or improve AGENTS.md and related documentation covering issue trackers, labels, architecture decisions, domain terms, validation commands, and which skills agents should use.
Why use it?
It prevents each new agent from having to rediscover how the repository works and reduces changes that ignore local conventions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Good fit Use it to create or improve AGENTS.md and related documentation covering issue trackers, labels, architecture decisions, domain terms, validation commands, and which skills agents should use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stark-ai-de/agent-skills/agent-context-bootstrap
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add stark-ai-de/agent-skills --skill agent-context-bootstrap
Clone the repo
git clone --depth 1 https://github.com/stark-ai-de/agent-skills

Made for: Claude Code, 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 agent-context-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/agent-context-bootstrap/github.svg)](https://agentmods.dev/skills/stark-ai-de/agent-skills/agent-context-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/agent-context-bootstrap"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/agent-context-bootstrap/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 agent-context-bootstrap

Your own site · 80×15
<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/agent-context-bootstrap"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/agent-context-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,242 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 $0.00054 $0.01242
Opus 5 $0.00027 $0.00621
Sonnet 5 $0.00011 $0.00248
Haiku 4.5 $0.00005 $0.00124

Measured 8d ago against content hash d58a05a8a9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-context-bootstrap 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 8d 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.

incubator/skills/repo-maintenance/agent-context-bootstrap/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Context Bootstrap

Goal

Create or improve repo-local agent context so future agents can work from the repository's real commands, docs, issue tracker rules, domain language, ADRs, validation commands, and skill routing without overwriting existing instructions.

When to use

  • A repository lacks AGENTS.md or agent-facing docs.
  • The user wants Codex, Claude Code, Cursor, or another agent to follow local workflow rules.
  • A repo needs issue tracker notes, triage labels, domain docs, ADR locations, or validation commands documented.
  • A downstream repo needs predictable first-run agent setup before using workflow skills.

When not to use

  • The user only wants a one-time handoff; use handoff.
  • The user wants a repo health report without changing context files; use repo-health-audit.
  • The repository already has clear agent instructions and the user did not ask for edits.
  • The user wants to publish a skill catalog; use skill-repo-curator.

Inputs to inspect

  • Existing AGENTS.md, CLAUDE.md, .codex/, .cursor/, CONTEXT.md, CONTEXT-MAP.md, and docs files.
  • README.md, package files, validation scripts, CI workflows, issue templates, labels, and .github/.
  • docs/adr/, architecture docs, domain docs, and existing docs/agents/.
  • Maintainer-provided issue tracker, triage labels, validation commands, runtime conventions, and domain-specific workflow notes.
  • git status --short before editing.

Workflow

  1. Inspect current agent instructions and docs before proposing edits.
  2. Infer what is safe from repo files: package manager, validation scripts, ADR location, CI commands, issue templates, and existing domain docs.
  3. Ask for maintainer input only when the repo cannot answer a hard setup decision: issue tracker, live label names, domain glossary location, validation command, or agent runtime convention.
  4. Create or update docs/agents/issue-tracker.md, docs/agents/triage-labels.md, docs/agents/domain-docs.md, docs/agents/validation.md, and docs/agents/skill-routing.md.
  5. Add or update an ## Agent skills block in the primary agent instruction file, usually AGENTS.md.
  6. Preserve existing user instructions and never overwrite unrelated sections.
  7. Validate links, formatting, and available repo checks.

Read the full file on GitHub · 126 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 126 lines · 54 tokens per session scan A d58a05a8a9a5

Subscribe to this mod's changes

agent-context-bootstrap is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,242 once invoked, about $0.0003 per session on Opus 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.