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 agentmods add rules/vypdev/copilot/project-contextgit clone --depth 1 https://github.com/vypdev/copilotWhat 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 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
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 yesterday.
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.
What it actually says
Copilot – Project Context
Quick read (for fast understanding)
- What it is: GitHub Action + CLI that automates Git-Flow: creates branches from issue labels, links issues/PRs to projects, tracks commits; AI via OpenCode (progress, errors, PR descriptions).
- Entry points: GitHub Action →
src/actions/github_action.ts; CLI →src/cli.ts. Shared logic insrc/actions/common_action.ts(single actions vs issue/PR/push). - Do: Use Node 20, run from repo root; edit only
src/; useINPUT_KEYS/ACTIONSandlogInfo/logError/logDebugInfo. When adding inputs: updateaction.yml,constants.ts(INPUT_KEYS), andgithub_action.ts(and optionallylocal_action.ts). - Don’t: Edit or depend on
build/(generated byncc); run tests/lint onbuild/.
Commands (repo root)
nvm use 20
npm install
npm run build
npm test
npm run test:watch
npm run test:coverage
npm run lint
npm run lint:fix
- Build:
npm run build→ bundlesgithub_action.tsandcli.tsintobuild/. - Tests: Jest;
npm run test:watch/npm run test:coverageas needed. - Lint: ESLint + typescript-eslint on
src/;npm run lint:fixto auto-fix.
What to ignore
build/– Generated output; do not edit or run tests/lint against it..agent-sessions/– Session data; ignore unless debugging.
Other rules
- Architecture & paths: see
architecture.mdc(entry points, use cases, single actions, key files). - Code conventions: see
code-conventions.mdc(logger, constants, adding inputs, ncc).
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.
- yesterday First seen · 41 lines · 469 tokens per session scan A e0e721a08d9f
project-context is a cursor rule published in the GitHub repository vypdev/copilot (2 stars, last pushed yesterday), licensed MIT. It adds 469 tokens to every session, about $0.0023 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 cursor rules, from other repositories
code-review-en
Code Review Guidelines (English).
code-review
代码审查规范（中文版）.
cursorrules
See AGENTS.md — Cursor reads it natively.
task-summary
Enforce Summary and Session Log blocks on every coding response when session tracking is enabled.
api-steps
How to create HTTP endpoints in Motia.
virtual-steps
Connecting nodes virtually and creating a smooth flow in Workbench.