agentmods.dev

bootstrap-agent-context

bootstrap-agent-context is a skill for Claude Code, Codex from varutasu/agent-pipeline. It costs 262 tokens per session (11,236 once invoked), scanned A, original, MIT.

A set of repository files that gives coding agents shared instructions, defined roles, and an optional workflow for taking an idea through development. It creates drafts such as AGENTS.md, Cursor rules, agent role files, and project automation files.

In plain words
What is it for?
Use it to add agent guidance to a repository, define specialized development roles, map a database schema, and set up optional pull-request and CI workflow support.
Why use it?
It helps agents understand a codebase and follow consistent working practices instead of rediscovering project context in every conversation. It also leaves changes for the developer to review rather than committing or pushing them automatically.

Skill for Claude CodeCodex

not rated 2 26d ago A scan 262 tokens original MIT
View the source file varutasu/agent-pipeline
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.

agentmods
npx agentmods add skills/varutasu/agent-pipeline/bootstrap-agent-context
Any agent
npx skills add varutasu/agent-pipeline --skill bootstrap-agent-context
Clone the repo
git clone --depth 1 https://github.com/varutasu/agent-pipeline

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 bootstrap-agent-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/varutasu/agent-pipeline/bootstrap-agent-context.svg)](https://agentmods.dev/skills/varutasu/agent-pipeline/bootstrap-agent-context)
Your own site
<a href="https://agentmods.dev/skills/varutasu/agent-pipeline/bootstrap-agent-context"><img src="https://agentmods.dev/badge/skills/varutasu/agent-pipeline/bootstrap-agent-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 262 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00262 $0.11236
Opus 5 $0.00131 $0.05618
Sonnet 5 $0.00052 $0.02247
Haiku 4.5 $0.00026 $0.01124

Measured 4d ago against content hash fee783ecd7f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap-agent-context 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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (templates/L1-context/generate-schema-map.ts, templates/L3-pipeline/_common/log-convoy-event.sh, templates/L3-pipeline/_common/wt.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/bootstrap-agent-context/SKILL.md · 637 lines

How it starts

The opening of the file, as written. The whole thing — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap Agent Context

Drafts a three-layer system so AI agents can orient and execute consistently across repos. Never commits, never pushes, never auto-runs roles. Every artifact is a draft for the user.

The three layers

Layer What it ships Always loaded? Per-repo?
L1 — Context AGENTS.md, .cursor/rules/, .cursor/skills/, schema map Yes (rules are glob-scoped) Yes
L2 — Roles 9 .cursor/agents/role-*.md files defining the pipeline subagents Loaded on invocation Yes
L3 — Pipeline CI workflows, PR template, CODEOWNERS, .convoys/ folder, optional flag wrapper, optional worktree helper Repo infra; runs on PRs Yes (stack-specific)

L1 stands alone (validated -53% conversation tokens in colab). L2 stands alone (you can run roles manually with no CI). L3 stands alone (you can run CI without roles). Together they form the idea-to-feature pipeline.

Hard rules

  • Never overwrite an existing file blindly. Always read first, propose a diff, and ask before replacing.
  • Never commit, push, or run git add. Stop after files are written so the user can review the diff.
  • Templates are starting points. Tailor them to the repo. If a template doesn't fit, omit or rewrite it.
  • Line budgets (each line must pass: "would removing this cause a mistake the agent wouldn't otherwise make?"):
    • AGENTS.md ≤120 lines
    • Always-apply rules (alwaysApply: true): ≤80 lines per file AND ≤80 lines combined across all always-apply rules
    • Glob-scoped rules: ≤120 lines per file (these only load when matching files are open, so they cost less; spend the headroom on documenting coexisting patterns honestly)
    • Each L2 role file: ≤100 lines
    • Each skill: ≤200 lines
    • Going over budget is allowed when justified (e.g. documenting two coexisting patterns that the agent will keep mixing up otherwise) — call it out in the hand-off so the user can choose to tighten
  • Never auto-spawn other roles. L2 roles hand off by message to the user, not by invoking siblings. Human gates are non-negotiable.

Read the full file on GitHub · 637 lines

Files

What ships with it

60 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. 4d ago First seen · 637 lines · 262 tokens per session scan A fee783ecd7f4

Subscribe to this mod's changes

bootstrap-agent-context is a skill published in the GitHub repository varutasu/agent-pipeline (2 stars, last pushed 26d ago), licensed MIT. It adds 262 tokens to every session and 11,236 once invoked, about $0.0013 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.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens