project-context-bootstrap

project-context-bootstrap is a skill for Codex from markoblogo/abvx-agent-skills. It costs 72 tokens per session (595 once invoked), scanned A, original, MIT.

A project-onboarding process that builds a clear, durable understanding of an unfamiliar code repository before major implementation work. It identifies the technology stack, structure, commands, verification paths, and existing agent-facing documentation.

In plain words
What is it for?
Use it when entering a new repository, installing agent workflows, checking project documentation, or preparing context for long-running work.
Why use it?
It reduces guesswork and prevents agents from relying on stale, missing, or conflicting project information.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it when entering a new repository, installing agent workflows, checking project documentation, or preparing context for long-running work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markoblogo/abvx-agent-skills/project-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 markoblogo/abvx-agent-skills --skill project-context-bootstrap
Clone the repo
git clone --depth 1 https://github.com/markoblogo/abvx-agent-skills

Made for: 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 project-context-bootstrap

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/project-context-bootstrap"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/project-context-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 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 $0.00072 $0.00595
Opus 5 $0.00036 $0.00298
Sonnet 5 $0.00014 $0.00119
Haiku 4.5 $0.00007 $0.00060

Measured 9d ago against content hash abf148a9f170, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

project-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 9d 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.

skills/project-context-bootstrap/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context Bootstrap

Create a compact, durable working model of a repo before the agent starts inventing one from guesswork.

Goal

Turn a repo with weak or missing agent-facing context into a repo with:

  • a clear stack and structure summary;
  • known commands and verification paths;
  • durable context files or notes with real content;
  • explicit approval before reorganizing existing docs.

Workflow

  1. Detect
    • inspect project manifests, lockfiles, workspace layout, test commands, and major directories;
    • detect whether context already exists: AGENTS.md, docs/ai/, runbooks, plans, or other agent-facing docs.
  2. Study existing context first
    • if the repo already has useful docs, read them before proposing replacements;
    • separate what looks good, stale, missing, or conflicting.
  3. Ask
    • have a real project-discovery conversation with the user;
    • cover what the product is, who uses it, main features, risky areas, workflow conventions, and external dependencies;
    • follow up until the project is actually understandable.
  4. Summarize
    • restate your understanding in concise project language;
    • confirm accuracy before writing or reorganizing context.
  5. Propose
    • suggest the smallest useful context structure:
      • top-level AGENTS.md or compact startup doc;
      • docs/ai/architecture.md;
      • docs/ai/how-to-test.md;
      • task-specific notes only if needed;
    • ask before reorganizing or overwriting anything durable.
  6. Populate
    • write real content from code and user input, not placeholders;
    • include concrete commands, file paths, key modules, and current conventions.
  7. Validate
    • verify the new context is small, accurate, and actually useful for the next session.

Existing Repo Rules

  • Preserve good context; do not replace it with generic scans.
  • Show what you want to keep, improve, and add before changing layout.
  • Never silently move or delete user-written docs.

Compression Rules

Read the full file on GitHub · 66 lines

Files

What ships with it

2 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. 9d ago First seen · 66 lines · 72 tokens per session scan A abf148a9f170

Subscribe to this mod's changes

project-context-bootstrap is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 595 once invoked, about $0.0004 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 2026-09-03.