agora-code

A skill for using Agora Code memory tools, which save and retrieve context across coding sessions. It covers injecting context, summarizing large files, recalling work, recording findings, and checkpointing progress.

In plain words
What is it for?
It is for loading prior session information, summarizing files before inspection, saving discoveries, tracking progress, checking project status, and closing a completed session.
Why use it?
It helps an agent continue work with earlier context and avoid reading large files unsafely or inefficiently.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/thebnbrkr/agora-code/agora_code
Any agent
npx skills add thebnbrkr/agora-code --skill agora_code
Clone the repo
git clone --depth 1 https://github.com/thebnbrkr/agora-code

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 863 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00863
Opus 5 $0.00014 $0.00432
Sonnet 5 $0.00006 $0.00173
Haiku 4.5 $0.00003 $0.00086

Measured 2d ago against content hash 05a1cd839d1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agora-code 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.

The scan reads SKILL.md. This mod also ships 11 executable files (__init__.py, cli.py, compress.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

91% identical to agora-code — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agora_code/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STOP — before you do anything else: Run agora-code summarize <file> before reading ANY file over ~50 lines. Do NOT use Read, shell commands (cat, head, tail, etc.), or an Explore subagent on a large file without summarizing first. This is not optional. The Explore subagent is mechanically blocked. Shell commands bypass hooks — don't use them to read files.

agora-code gives you persistent memory across sessions. Hooks handle most things automatically, but you must follow the rules below — they are not optional.

Your rules (always follow these)

  1. Before reading any file over ~50 lines — run agora-code summarize <file> first. Do not use the Read tool or an Explore subagent on a large file without summarizing first. This is mandatory, not optional.
  2. At session start — run agora-code inject to load prior context (checkpoints, learnings, git state, symbol index).
  3. When done with a task — run agora-code complete --summary "..." to archive the session.
  4. Always run agora-code status -p (not status) to see per-project stats.
  5. Do not ask the user to set a goal — infer it from what they're working on.

What the hooks handle automatically (no action needed)

Hook Event Does
pre-agent.sh PreToolUse(Agent) Blocks Explore subagent — hooks don't fire inside subagents
pre-read.sh PreToolUse(Read) Intercepts large files — auto-summarizes before Claude reads
on-read.sh PostToolUse(Read) Indexes symbols + code blocks into DB
on-grep.sh PostToolUse(Grep) Indexes files matched by grep into DB
on-edit.sh PostToolUse(Write/Edit) Re-indexes symbols, tracks diff
on-bash.sh PostToolUse(Bash) Tags committed files with SHA on git commit
on-prompt.sh UserPromptSubmit Auto-sets goal, recalls relevant learnings
on-stop.sh Stop Parses transcript → structured checkpoint

PostCompact re-injects context automatically after context compaction.

Read the full file on GitHub · 77 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 77 lines · 28 tokens per session scan A 05a1cd839d1c

Subscribe to this mod's changes

agora-code is a skill published in the GitHub repository thebnbrkr/agora-code (46 stars, last pushed 13d ago), licensed Apache-2.0. It adds 28 tokens to every session and 863 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to agora-code, differing in 6 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens