Skip to content
Back to skills

Project Context

ASecurity

Read, write and extend docs/agents/project-context.md, the 150-line binding rules file executor agents load before code. Use with /orc:context.

  • 7 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 10, 2026
ai-agentsdocumentation

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 10, 2026

npx -y skills add HigorAlves/orc --skill project-context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project Context?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Project Context
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/higoralves-project-context-orc/badge)](https://www.skillsdirectory.com/skills/higoralves-project-context-orc)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: project-context
description: Read, write and extend docs/agents/project-context.md, the 150-line binding rules file executor agents load before code. Use with /orc:context.
---

# Project Context

`.orc/` dies at cleanup. `docs/agents/project-context.md` does not. It carries a repo's implementation conventions across branches, sessions and agents.

## What it is

- Directives to agents: "use X, never Y, here".
- Project-specific facts a model would guess wrong.
- Committed, shared with the team.

It is not documentation for humans, a plan, or session state. Architecture prose belongs in `docs/adr/`. Vocabulary belongs in `GLOSSARY.md`.

Line test: would a competent engineer new to this repo get it wrong without the line? If no, cut it. Rubric and worked example: [FORMAT.md](references/FORMAT.md).

## Cap

**150 lines / 6 KB, hard.** Executors preload this file on every task, so the cap is a per-task token cost. State the cap in the file header. `scripts/ci/verify-project-context.sh` fails above 150 lines or 6144 bytes. Cut before you add.

## Sections

Keep this order. Omit a section that would be empty.

1. Stack & versions
2. Commands (test, lint, typecheck, build)
3. Critical rules
4. Patterns to follow
5. Patterns to avoid
6. Known landmines

## Binding semantics

Critical rules are binding. A slice that needs to break one escalates. The caller decides: the rule is stale, or the slice is wrong.

Other sections are strong defaults. Deviate only with a stated reason in the slice report.

## Who reads it

- Four agents preload this skill: `orc-implementer`, `orc-test-author`, `orc-code-fixer`, `orc-qa-validator`.
- Each reads the file once, before discovery.
- A missing file is the default state. Proceed silently, never gate on it.

## Who writes it

- `/orc:context` generates, refreshes and appends. Executors never write the file.
- `/orc:retro` proposes additions from repeated incidents.
- Each proposal passes the line test and the cap, and lands only through a gate.

Files in this skill

  • SKILL.md2 KB
  • references/FORMAT.md1.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.