agentmods.dev

SwarmAI: Instructions file for Kiro

.kiro/steering/context-and-memory-safety.md

SwarmAI context-and-memory-safety.md is an instructions file for Kiro from xg-gh-25/SwarmAI. It costs 1,349 tokens per session, scanned A, original, MIT.

A set of instructions for loading an AI system's context and memory safely. It defines priorities for files such as user details, project information, stored memories, and domain knowledge, while allowing startup to continue if loading fails.

In plain words
What is it for?
Use it when changing context-file loading, memory handling, prompt assembly, file copying, or token-budget rules.
Why use it?
It prevents missing or damaged context from stopping the agent and helps decide which information to keep when space is limited.

Instructions file for Kiro

Written for Kiro: installed under .kiro/. Also seen: mentions AGENTS.md.

This is xg-gh-25/SwarmAI's own configuration. It tells Kiro how to work on SwarmAI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SwarmAI configures →

not rated 55repo +1 changed 8d ago A scan 1,349 tokens original MIT
View source ↗ xg-gh-25/SwarmAI
Reuse

Borrowing it

Nothing to install: this file belongs to xg-gh-25/SwarmAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xg-gh-25/SwarmAI/main/.kiro/steering/context-and-memory-safety.md
Clone the repo
git clone --depth 1 https://github.com/xg-gh-25/SwarmAI

Made for: Kiro.

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 SwarmAI context-and-memory-safety.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/context-and-memory-safety/github.svg)](https://agentmods.dev/instructions/xg-gh-25/swarmai/context-and-memory-safety)
Your own site
<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/context-and-memory-safety"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/context-and-memory-safety/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for SwarmAI context-and-memory-safety.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/context-and-memory-safety"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/context-and-memory-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,349 This file is loaded in full into every session.
When invoked 1,349 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01349 $0.01349
Opus 5.5 $0.00540 $0.00540
Sonnet 5.5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 8d ago against content hash 711d5af6b8c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SwarmAI context-and-memory-safety.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 8d 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.

.kiro/steering/context-and-memory-safety.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context and Memory Safety Principles

The file list, priorities, and budgets are summarized in AGENTS.md "Context and Memory System". The source of truth is CONTEXT_FILES and compute_token_budget in backend/core/context_directory_loader.py. This file covers the invariants that are easy to break.

Core Invariant: Context Loading Never Blocks Agent Startup

The assembly pipeline (ContextDirectoryLoader.load_all() → PromptBuilder.build_system_prompt() in prompt_builder.py → SystemPromptBuilder.build()) must degrade gracefully. A failure at any stage starts the agent with reduced context; it never crashes the session.

Ownership and Two-Mode Copy (ensure_directory)

These rules are the user trust model. Violating them destroys user customizations.

  1. System files (user_customized=False: SWARMAI, IDENTITY, SOUL, AGENT) are ALWAYS overwritten from the template, only when the bytes changed, and set to 0o444.
  2. Everything with user_customized=True (SELF, USER, STEERING, TOOLS, MEMORY, EVOLUTION, KNOWLEDGE) is copied ONLY if missing and never overwritten (0o644). SELF.md is runtime-owned: the live .context/SELF.md is authoritative, so a template edit does not reach an existing install.
  3. New context files go into CONTEXT_FILES with an explicit priority and ownership. PROJECTS.md was removed (2026-08-14); don't reintroduce an auto-generated index file.

Token Budget: Warn, Never Truncate

  • Budget tiers (compute_token_budget): ≥500K window → 150K, ≥200K → 50K, ≥64K → 30K, <64K → instance default (L0 compact path). Below 32K, KNOWLEDGE.md is skipped.
  • The read-line NEVER truncates. Over budget, _enforce_token_budget logs an over_budget warning and returns full content. _truncate_section was deleted on 2026-08-14; the truncatable/direction fields are legacy and inert.
  • Size is bounded WRITE-side: MEMORY distillation + size-valve archival, and the EVOLUTION size valve (20K high / 15K low watermark → monthly archive shard). If a file is too big, fix the write-side valve, not the loader.
  • Don't flip truncatable to False on MEMORY/EVOLUTION: core_section_names() treats truncatable is False as "conceptual core".

Read the full file on GitHub · 102 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. 8d ago Changed · -15 lines · -221 tokens per session 711d5af6b8c3
  2. 1mo ago First seen · 117 lines · 1,570 tokens per session scan A 3f931a05d85e

Subscribe to this mod's changes

SwarmAI context-and-memory-safety.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (55 stars, last pushed 8d ago), licensed MIT. It adds 1,349 tokens to every session, about $0.0054 per session on Opus 5.5. 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 2026-09-06.

Building agentsMemory and contextagentic-aiai-agentaws-bedrockclaudeclaude-sdkcontext-engineering
Related

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens