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 instructions/selimozten/elek/agents-mdgit clone --depth 1 https://github.com/selimozten/elekWrote 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/instructions/selimozten/elek/agents-md)<a href="https://agentmods.dev/instructions/selimozten/elek/agents-md"><img src="https://agentmods.dev/badge/instructions/selimozten/elek/agents-md.svg" alt="Measured on agentmods" 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 | $0.01987 | $0.01987 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade B, and why
elek AGENTS.md scanned grade B with 1 finding 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 3d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**`.mcp.json` carries `GITHUB_TOKEN`.** Written to How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents working in this repository. Read before editing.
What this is
elek is a model-agnostic GitHub Action that runs AI code reviews on pull requests and issues. It wraps pi coding agent and adds a tightly-scoped tool surface — the model can post inline review comments and update its tracking comment, but cannot approve, merge, or close a PR. That guarantee is structural: there is no plumbing to those endpoints. Don't add it casually.
How it runs
Composite GitHub Action. Single TypeScript orchestrator at
src/entrypoints/run.ts runs end-to-end:
flowchart TD
A[GitHub event] --> B[parse context]
B --> C[detect trigger]
C --> D[fetch PR / issue data]
D --> E[build XML-tagged prompt]
E --> F["spawn pi --mode json<br/>(stdio: ignore — pi hangs without it)"]
F --> G[parse events,<br/>drive progressive comment updates]
G --> H[drain inline-comment buffer]
H --> I[post review comments]
Pi is run via the CLI (not the SDK) so we stay model-agnostic — any provider pi supports, elek supports.
File map
action.yml Composite GitHub Action declaration.
src/entrypoints/run.ts Main orchestrator. Read this first.
src/entrypoints/post-buffered.ts Drains MCP buffer; posts inline comments.
src/pi.ts pi CLI runner; parses --mode json events.
src/types.ts Shared types.
src/github/context.ts Parses the GitHub webhook payload.
src/github/trigger.ts @pi mention detection, actor filtering.
src/github/data.ts PR/issue data fetch + buildPrompt().
src/github/comments.ts Tracking-comment lifecycle.
src/github/progress.ts Live checklist body.
src/github/spinner.ts Animated elek SVG header.
src/github/mode.ts review / review+edit / agent presets.
src/github/git.ts git auth + branch ops.
src/mcp/handlers.ts Pure handler logic (testable, deps-injected).
src/mcp/github-review-server.ts Thin McpServer shim around handlers.
test/*.test.ts Bun test, integration-style.
docs/ARCHITECTURE.md Deeper system overview.
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.
- 3d ago First seen · 176 lines · 1,987 tokens per session scan B 822432582d17
elek AGENTS.md is an instructions file published in the GitHub repository selimozten/elek (19 stars, last pushed 10d ago), licensed MIT. It adds 1,987 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
academic-commercialization-agent AGENTS.md
Instructions for shuxiachai/academic-commercialization-agent, covering agents.md — working on this project, what it is, commands, hard conventions and where the reasoning lives.
cherry-studio AGENTS.md
AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
Tianshu-harness CLAUDE.md
Instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
rikkahub AGENTS.md
AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.
writing-agent CLAUDE.md
Instructions for dongbeixiaohuo/writing-agent, covering 写稿 agent 核心路由指令（v0.10.0） and 路由顺序.