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 | $0.01475 | $0.01475 |
| Opus 5.5 | $0.00590 | $0.00590 |
| Sonnet 5.5 | $0.00295 | $0.00295 |
| Haiku 4.5 | $0.00147 | $0.00147 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 94 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
Priority ordering (ADL Protocol): Stability > Interpretability > Reusability > Extensibility > Novelty. The model proposes; code gates. Nothing in the evolution system may auto-write the governed judgment files (SOUL / AGENT / STEERING) — it writes proposals for a human.
The Three Evolution Paths (current)
| Path | Trigger | Code | Writes |
|---|---|---|---|
| Skill-optimization cycle (MINE→ASSESS→ACT→AUDIT) | Weekly system job evolution-cycle (Thu 07:00, 1800s timeout) — the ONLY trigger |
evolution_optimizer.run_evolution_cycle via jobs/run_evolution.py |
skill_health.json, .evolution_proposals.json, EVOLUTION.md + changelog |
| EVOLUTION.md maintenance | Session close (EvolutionMaintenanceHook, post-session hook) |
hooks/evolution_maintenance_hook.py |
EVOLUTION.md, monthly archive shard, changelog |
| Governance lifecycle | Prompt-driven | s_self-evolution skill (CLASSIFY/CAPTURE/PROMOTE/REFINE/RETIRE/COMPRESS) |
EVOLUTION.md via Read + Edit, changelog |
Never put the cycle back on the session-close hook: it takes ~5 min against a 180s hook budget and re-fired every session (run_6ac3fc0b).
Cycle Guardrails (code-enforced, evolution_optimizer.py)
- Process flock on
.evolution_cycle.lock(non-blocking, stale-lock break) — one cycle at a time. - LLM cost cap:
evolution.max_llm_skills_per_cycle(default 5), highest confidence first. - Confidence tiers: HIGH → proposal/deploy, MED → recommendation, LOW → log only. HIGH needs ≥2 corrections, else it is demoted to MED.
- Regression gate: a deployed skill whose fitness dropped >0.1 is auto-reverted from
SKILL.md.bak. Deploys are atomic (tmp +os.replace+ verify + rollback). - Freshness re-read before applying changes (the skill may have changed since MINE).
- Thresholds:
HIGH_CONFIDENCE = 0.15,MED_CONFIDENCE = 0.08inevolution_optimizer.pyare the ONLY source (not configurable; a test guards against a second source). Recalibrate them there, with data.
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.
- 8d ago Changed · -17 lines · -123 tokens per session dd277aa30736
- 1mo 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 (55 stars, last pushed 8d ago), licensed MIT. It adds 1,475 tokens to every session, about $0.0059 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.
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).
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.
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).
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.
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).
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.