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/thebnbrkr/agora-code/claude-mdgit clone --depth 1 https://github.com/thebnbrkr/agora-codeWhat 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 | $0.00743 | $0.00743 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
agora-code CLAUDE.md 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agora-code — Claude Code Instructions
HARD RULES — enforced by hooks, do not bypass
- NEVER use the Explore subagent — it bypasses agora-code hooks. Use
Read/Grep/Globdirectly. ThePreToolUse(Agent)hook will block it. - NEVER call
Readon a file >50 lines without runningagora-code summarize <file>first — thepre-read.shhook enforces this too.
These are mechanical constraints, not preferences.
This project provides persistent memory and API discovery for AI agents.
How it works
Everything is automatic via Claude Code hooks. When you read a file, symbols and code blocks are indexed. When a session ends, the transcript is parsed into a structured checkpoint. On every prompt, relevant learnings are recalled.
You do not need to manually run agora-code learn or agora-code recall — the hooks handle it.
Always do this
- At session start, run
agora-code injectto load previous session context - STOP — before ANY Read tool call on a file over ~50 lines:
- Run
agora-code summarize <file>first - Then use
offset+limitto read ONLY the sections you need Skipping this wastes the entire point of the tool.
- Run
- After every file edit, run:
Write what function/class changed, what it calls/depends on and where, and the outcome. Tagagora-code track-diff <file> --note "one sentence: what changed and why"#not_keptif you reverted — kept changes are auto-tagged#kepton commit. Example:"tried caching in validate_user() via redisupload() in redis_db.py to reduce DB hits — didn't work #not_kept"
Tool reference
| Command | When to use |
|---|---|
agora-code inject |
Session start — loads structured checkpoint, learnings, git state, symbol index |
agora-code summarize <file> |
Before reading large files — 75%+ token reduction |
agora-code learn "<text>" |
Force-save a specific finding right now (optional — auto-done by on-stop.sh) |
agora-code recall "<query>" |
Search past findings (optional — auto-done by on-prompt.sh) |
agora-code checkpoint --goal "..." |
Save progress mid-task |
agora-code status |
Check current session and DB stats |
agora-code complete --summary "..." |
Archive session to long-term memory when done |
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.
- 2d ago First seen · 62 lines · 743 tokens per session scan A 90b7ccdd8538
agora-code CLAUDE.md is an instructions file published in the GitHub repository thebnbrkr/agora-code (46 stars, last pushed 13d ago), licensed Apache-2.0. It adds 743 tokens to every session, about $0.0037 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.