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 JakubMikolajek/codex-skills-collection --skill project-contextgit clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collectionWrote 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/jakubmikolajek/codex-skills-collection/project-context)<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/project-context"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/project-context/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/jakubmikolajek/codex-skills-collection/project-context"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/project-context.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 | $0.00037 | $0.01177 |
| Opus 5 | $0.00018 | $0.00589 |
| Sonnet 5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context
This skill provides a systematic approach for building project understanding at the start of any non-trivial session. It produces a Session Context Block that anchors all subsequent work to verified facts about the project's stack, conventions, and constraints.
When to Use
- At the start of any non-trivial session
- When switching to a different repo or branch mid-session
- Before running
architecture-design,code-review, orimplementation-gap-analysis - When a teammate's task description references unfamiliar parts of the codebase
When NOT to Use
- Task is a simple one-line answer or clarification question — do not run full context discovery
- Session Context Block was already produced in the current session and no branch/repo switch occurred
- Task explicitly says "skip context" or provides all context inline
Core Principles
Read Before Assuming
- Never infer stack or conventions from a single file — require at least 2 confirming sources
- If evidence conflicts, state the conflict explicitly — do not resolve it silently
- Do not guess business logic, framework version, or team decisions without evidence
- Treat the Session Context Block as a living document — update it when new evidence appears
What to Read on Session Start
Read in this order, stopping once the Session Context Block can be filled:
- Root manifest:
package.json/pubspec.yaml/build.gradle/Cargo.toml(whichever exists) README.mdat repo rootAGENTS.md— check.codex/AGENTS.mdfirst (primary location in bootstrapped projects), then repo root as fallback. Read the Skill Routing table and path convention note.skills/routing/branch files (relative toAGENTS.md's directory) — extract active skills and combination rules- Folder structure — max 2 levels deep
- One representative source file per detected layer (e.g. one component, one service, one test)
Session Context Block
Produce this block at the top of the first response, max 20 lines:
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.
- 12d ago First seen · 117 lines · 37 tokens per session scan A a0aef356dbd9
project-context is a skill published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 1,177 once invoked, about $0.0002 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.
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…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…