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.
curl -O https://raw.githubusercontent.com/xg-gh-25/SwarmAI/main/.kiro/steering/self-evolution-guardrails.mdgit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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.
[](https://agentmods.dev/instructions/xg-gh-25/swarmai/self-evolution-guardrails)<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/self-evolution-guardrails"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/self-evolution-guardrails/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.
<a href="https://agentmods.dev/instructions/xg-gh-25/swarmai/self-evolution-guardrails"><img src="https://agentmods.dev/badge/instructions/xg-gh-25/swarmai/self-evolution-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.01598 | $0.01598 |
| Opus 5 | $0.00799 | $0.00799 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
SwarmAI self-evolution-guardrails.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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Evolution Guardrails
Core Invariant: Evolution Improves Stability, Not Complexity
The self-evolution system is prompt-driven by design. The agent detects capability gaps, builds solutions, and persists them in EVOLUTION.md. Backend code provides infrastructure only: file provisioning, SSE event parsing, config defaults, and locked writes.
Priority ordering (ADL Protocol): Stability > Interpretability > Reusability > Extensibility > Novelty
What Is Code-Enforced vs Prompt-Dependent
| Layer | Mechanism | Reliability |
|---|---|---|
| EVOLUTION.md loading at P8 | ContextDirectoryLoader |
Code-enforced |
| EVOLUTION.md provisioning | ensure_directory() |
Code-enforced |
| SSE event marker parsing | _extract_evolution_events() regex in chat.py |
Code-enforced |
| Frontend evolution rendering | useChatStreamingLifecycle + EvolutionMessage |
Code-enforced |
| EvolutionBadge wiring | deriveEvolutionCounts in ChatPage → SwarmRadar prop |
Code-enforced |
| Config defaults | AppConfigManager evolution key |
Code-enforced |
| Entry deprecation + pruning | EvolutionMaintenanceHook at session close |
Code-enforced |
| Tool failure trigger nudge | ToolFailureTracker in message loop |
Code-enforced |
| Trigger detection | s_self-evolution/SKILL.md instructions |
Prompt-dependent (code-assisted) |
| Evolution loop execution | s_self-evolution/SKILL.md instructions |
Prompt-dependent |
| EVOLUTION.md writes | Agent uses Read+Edit / locked_write.py |
Prompt-dependent |
| Entry dedup before write | s_self-evolution/SKILL.md Step 0 procedure |
Prompt-dependent |
| JSONL changelog | Agent appends after every Edit | Prompt-dependent |
SSE Event Flow — Do Not Break the Chain
Agent text → <!-- EVOLUTION_EVENT: {...} --> marker
→ _extract_evolution_events() regex parse in chat.py
→ Separate SSE data line emitted by sse_with_heartbeat()
→ Frontend: event.type.startsWith('evolution_') check
→ Message with evolutionEvent property → EvolutionMessage component
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.
- 3d ago First seen · 111 lines · 1,598 tokens per session scan A 340233636aa3
SwarmAI self-evolution-guardrails.md is an instructions file published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 2d ago), licensed MIT. It adds 1,598 tokens to every session, about $0.0080 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 2026-09-06.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.