ccstory AGENTS.md

ccstory AGENTS.md is an instructions file for Codex, OpenCode from atomchung/ccstory. It costs 896 tokens per session, scanned A, original, MIT.

Repository instructions for ccstory, a local-first Python command-line tool and library that turns conversations into structured stories. They define shared rules for coding agents and how instructions are divided between tools.

In plain words
What is it for?
Use them when changing ccstory, deciding where project facts or agent rules belong, handling concurrent work, or following its development and verification process.
Why use it?
They keep repository guidance in the right place and reduce conflicting rules between Codex, Claude Code, and other agents.

Instructions file for CodexOpenCode

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 instructions/atomchung/ccstory/agents-md
Clone the repo
git clone --depth 1 https://github.com/atomchung/ccstory

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for ccstory AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atomchung/ccstory/agents-md.svg)](https://agentmods.dev/instructions/atomchung/ccstory/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/atomchung/ccstory/agents-md"><img src="https://agentmods.dev/badge/instructions/atomchung/ccstory/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 896 This file is loaded in full into every session.
When invoked 896 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00896 $0.00896
Opus 5 $0.00448 $0.00448
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00090 $0.00090

Measured 3d ago against content hash 56008d897f1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccstory AGENTS.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 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.

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.

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ccstory agent guide

This is the canonical repository guide for coding agents. Codex and Antigravity read it directly; Claude Code reads it through the thin CLAUDE.md import. Keep shared rules here rather than copying them into tool-specific files.

Instruction layers

  • Neutral product facts belong in the code, README.md, architecture docs, or ADRs. Do not turn this file into a second product encyclopedia.
  • Shared expectations for how any coding agent should work belong here.
  • Claude Code-only deltas belong below the @AGENTS.md import in CLAUDE.md.
  • Antigravity-only deltas belong in GEMINI.md or .agents/rules/ when a real Antigravity-specific need appears.
  • Codex-only settings belong in .codex/config.toml. Use its developer_instructions only for short Codex-specific behavioral additions; keep shared behavior in this file.
  • Prefer a tool-neutral intent here over parallel tool recipes. For example, say what evidence is required, then let each agent use its closest native capability. Create a tool-specific delta only when the behaviors genuinely cannot be the same.

Repository contract

  • ccstory is a local-first Python 3.11+ CLI and library that turns Claude Code, Codex, and Antigravity session logs into recaps, trends, JSON, and read-only MCP results.
  • Preserve behavior across every user-facing surface affected by a change: terminal cards, Markdown reports, JSON, trend/comparison output, and MCP.
  • Keep provider-specific parsing under ccstory/providers/. Shared attribution, usage, pricing, recap, and rendering logic stays provider-neutral.
  • Never estimate token usage or infer a model when the source does not expose authoritative values. Keep incomplete coverage and unknown prices explicit through the existing usage_coverage and unpriced_models lanes.
  • Preserve the local-data boundary documented in README.md. Do not add telemetry or send transcript content to metadata services.

Concurrent-agent safety

Read the full file on GitHub · 89 lines

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. 3d ago First seen · 89 lines · 896 tokens per session scan A 56008d897f1a

Subscribe to this mod's changes

ccstory AGENTS.md is an instructions file published in the GitHub repository atomchung/ccstory (43 stars, last pushed 3d ago), licensed MIT. It adds 896 tokens to every session, about $0.0045 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.

Related

Other instructions, from other repositories