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.
npx skills add JuanColilla/Agentic-Agnostic-Workflow-Environment --skill agentic-environment-bootstrapgit clone --depth 1 https://github.com/JuanColilla/Agentic-Agnostic-Workflow-EnvironmentWrote 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.
[](https://agentmods.dev/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-bootstrap)<a href="https://agentmods.dev/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-bootstrap"><img src="https://agentmods.dev/badge/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-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.
<a href="https://agentmods.dev/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-bootstrap"><img src="https://agentmods.dev/badge/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00177 | $0.05257 |
| Opus 5 | $0.00088 | $0.02629 |
| Sonnet 5 | $0.00035 | $0.01051 |
| Haiku 4.5 | $0.00018 | $0.00526 |
Grade B, and why
agentic-environment-bootstrap scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
in `~/.claude/settings.json`, set `AGENTS_TIER=core|extended` in each How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Environment Bootstrap
Scaffold a project (or a fresh user account) so it works coherently with any AI coding agent through a single open-standard surface: AGENTS.md. Tool-specific files (CLAUDE.md, GEMINI.md, etc.) are reduced to thin adapters that delegate back to AGENTS.md.
Why this exists
The market has converged on AGENTS.md (Linux Foundation, Dec 2025) as the canonical contract for AI coding agents. Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenCode, Aider, Zed, Warp and most of the ecosystem read it natively. Only Claude Code still requires a CLAUDE.md adapter (anthropics/claude-code#6235, open since Aug 2025). This skill captures that reality: write the truth once in AGENTS.md, generate adapters for every tool the user has installed, never duplicate content.
Two further realities this skill encodes. Context tiers: one harness now serves both small-window local models (MLX-class, where every line of instructions costs prefill) and large-window providers — so directives split into a minimal core every model gets and extended tiers only high-capacity runtimes load (why: a rule that helps a 200k model actively hurts a 32k one; see references/context-tiers.md). Advanced agents: roles accumulate knowledge, corrections and preferences that outlive any single project or tool — so they are defined once as canonical bundles (role + knowledge + memory + skill-box) and compiled per tool (why: role continuity without vendor lock-in; see references/advanced-agents.md).
This skill (with its sibling doctor) is the complete, self-contained deployment vehicle for the whole system — global level and project level, greenfield (R1/Workflows A-D) and migration (R2). If deploying or converting requires knowledge that is not in this skill's references, that is a bug in the skill: fix the skill, don't improvise.
The full architectural rationale lives in references/architecture.md. Read it whenever the user pushes back on a decision — there is a sourced reason for every rule here.
What ships with it
28 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.
- assets/.gitignore.fragment 72 B
- assets/agent.md.template 1.1 KB
- assets/AGENTS.extended.md.template 671 B
- assets/AGENTS.md.template 2.7 KB
- assets/ARCHITECTURE.md.template 2.3 KB
- assets/CLAUDE.md.adapter.template 158 B
- assets/DESIGN.md.template 3.1 KB
- assets/GEMINI.md.adapter.template 160 B
- assets/MEMORY.md.template 356 B
- assets/tier-dispatch-hook.sh 1.0 KB runs code
- assets/tier-extended.md.template 935 B
- assets/tier-provider.md.template 601 B
- references/advanced-agents.md 7.1 KB
- references/architecture.md 6.2 KB
- references/context-tiers.md 3.3 KB
- references/live-library-pattern.md 6.5 KB
- references/migration-from-claude-only.md 6.7 KB
- references/skills-portability.md 3.8 KB
- references/three-level-hierarchy.md 2.3 KB
- references/tool-adapters.md 3.7 KB
- scripts/bootstrap-user-env.sh 19 KB runs code
- scripts/compile-adapters.sh 2.1 KB runs code
- scripts/compile-agents.py 6.6 KB runs code
- scripts/copy-mode-bootstrap.sh 2.4 KB runs code
- scripts/detect-tools.sh 6.3 KB runs code
- scripts/init-project.sh 6.9 KB runs code
- scripts/migrate-claude-md.py 7.1 KB runs code
- scripts/new-agent.sh 1.3 KB runs code
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.
- 8d ago First seen · 227 lines · 177 tokens per session scan B 3bc63db6e54a
agentic-environment-bootstrap is a skill published in the GitHub repository JuanColilla/Agentic-Agnostic-Workflow-Environment (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 177 tokens to every session and 5,257 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…