What is ai-context AGENTS.md?

A shared instruction file for AI coding assistants working on the ai-context project. It tells them which project notes, rules, plans, and session records to read and follow.

Use it to orient an agent, plan larger changes, apply project standards, and continue work from earlier sessions.

It keeps different assistants aligned with the same project context and reduces lost decisions between sessions.

ai-context AGENTS.md — Instructions file by dkothule

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/dkothule/ai-context/agents-md

Clone the repo

git clone --depth 1 https://github.com/dkothule/ai-context

Made for: Codex, OpenCode.

Per session 935 This file is loaded in full into every session.

When invoked 935 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.

Model	Per session	Once invoked
Fable 5	$0.00935	$0.00935
Opus 5	$0.00467	$0.00467
Sonnet 5	$0.00187	$0.00187
Haiku 4.5	$0.00093	$0.00093

Measured 2d ago against content hash f75914d6cd30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-context 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 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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Shared agent adapter

This file is intentionally thin. The single source of truth is .ai-context/, loaded on demand.

Read First (Every Session)

Always read for orientation:

.ai-context/project.overview.md
.ai-context/project.changelog.md
Latest file in .ai-context/sessions/ (excluding _archive/)

Then read based on task:

Writing/modifying code → .ai-context/standards/project.rules.base.md, project.rules.md
Planning non-trivial work → .ai-context/project.tasks.md, plans/
Understanding codebase layout → .ai-context/project.structure.md
Continuing prior work → additional files in sessions/
Language/testing specifics → files in .ai-context/standards/

Planning

Before non-trivial work (multi-session, architectural change, external dependency), write a plan to .ai-context/plans/YYYY-MM-DD-<topic>.md using _template.md. Reference the plan from project.tasks.md so it's discoverable. After plan approval, write the file immediately — before any implementation begins.

Execution Contract

Follow .ai-context/standards/project.rules.base.md and project.rules.md.
One logical change per commit; tests run before commit.
Keep .ai-context/ in sync with project state — route each change to the correct file:
- New architectural decision → project.decisions.md
- User-visible change → project.changelog.md
- Task transition (new/done/blocked) → project.tasks.md
- Plan authored → plans/YYYY-MM-DD-<topic>.md
- Session close → sessions/YYYY-MM-DD-<topic>.md

End-Of-Session (Mandatory)

Any repo-aware task (review, investigation, coding) is a session unless it's pure chat without repository access.

Write .ai-context/sessions/YYYY-MM-DD-<topic>.md from _template.md. Multiple logs per day are fine — one per topic.
Update project.tasks.md, project.decisions.md, project.changelog.md per the mapping above.

Hooks (per-agent)

AI Context installs session-management hooks to automate session logging and (where possible) preserve transcript context across compaction. Coverage by agent:

Read the full file on GitHub · 56 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.

2d ago First seen · 56 lines · 935 tokens per session scan A f75914d6cd30

Subscribe to this mod's changes

ai-context AGENTS.md is an instructions file published in the GitHub repository dkothule/ai-context (11 stars, last pushed 3mo ago), licensed MIT. It adds 935 tokens to every session, about $0.0047 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.

Planning Productivity

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

ai-context AGENTS.md