project-context

project-context is a skill for Claude Code, Codex from jasonkneen/lazar. It costs 0 tokens per session (705 once invoked), scanned A, original, MIT.

A project-reading procedure that checks a codebase's PROJECT.md, AGENTS.md, or related guidance before code changes.

In plain words
What is it for?
Use it before editing a project to learn its structure, language, conventions, build commands, and restrictions.
Why use it?
It prevents the agent from ignoring local rules or creating a separate implementation beside the existing one.

Skill for Claude CodeCodex

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

Good fit Use it before editing a project to learn its structure, language, conventions, build commands, and restrictions.

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

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 project-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/jasonkneen/lazar/project-context.svg)](https://agentmods.dev/skills/jasonkneen/lazar/project-context)
Your own site
<a href="https://agentmods.dev/skills/jasonkneen/lazar/project-context"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/project-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 705 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 $0.00000 $0.00705
Opus 5 $0.00000 $0.00352
Sonnet 5 $0.00000 $0.00141
Haiku 4.5 $0.00000 $0.00071

Measured 8d ago against content hash 5f071413c6a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-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 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.

src/seed-skills/_meta/project-context/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

project-context

Before modifying any code in a project directory, read the project's PROJECT.md (if present) to learn its conventions, structure, and rules. This prevents the most common drift: the agent inventing a parallel implementation instead of editing the one that exists.

When to use

  • The user references a directory or codebase ("the TUI", "the parser", "the lazartui").
  • You're about to write code under $LAZAR_HOME/workspace/<project>/ or similar.
  • You need to know "where does X live?" or "what language/framework does this project use?"

How to use

  1. Identify the project root. Usually it's:

    • The deepest directory containing PROJECT.md (or README.md if no PROJECT.md).
    • The deepest directory containing a manifest like go.mod, Cargo.toml, package.json.
  2. Read the project pin:

    cat <project-root>/PROJECT.md 2>/dev/null \
      || cat <project-root>/AGENTS.md 2>/dev/null \
      || ls <project-root>          # fall back to listing files
    
  3. Follow the conventions in PROJECT.md verbatim — language, file layout, build commands, "do not" rules.

  4. If PROJECT.md says "always read X first", do that next.

  5. If there is NO PROJECT.md, infer from the manifest and existing files. Read the entry point (main.go, src/lib.rs, index.ts) before suggesting changes.

Hard rules

  • Never create parallel implementations. If main.go exists, modify main.go. Don't write main2.go "to experiment". If you need to experiment, branch with git, not with file proliferation.
  • Don't introduce new languages or frameworks unless PROJECT.md explicitly invites it. The presence of go.mod means Go is the language; don't suddenly add Python.
  • Read before writing. For any non-trivial edit, read the file you're about to modify in full. Patch in place; don't rewrite.
  • Stay inside the project root. Don't create new directories at the workspace level "for organization" unless asked.

Anti-patterns to recognize in yourself

Read the full file on GitHub · 57 lines

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 · 57 lines · 0 tokens per session scan A 5f071413c6a8

Subscribe to this mod's changes

project-context is a skill published in the GitHub repository jasonkneen/lazar (31 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 705 tokens. 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 2026-08-30.

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

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 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