Borrowing it
Nothing to install: this file belongs to Shangri-la-0428/Thronglets. 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/Shangri-la-0428/Thronglets/main/AGENTS.mdgit clone --depth 1 https://github.com/Shangri-la-0428/ThrongletsWrote 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/shangri-la-0428/thronglets/agents-md)<a href="https://agentmods.dev/instructions/shangri-la-0428/thronglets/agents-md"><img src="https://agentmods.dev/badge/instructions/shangri-la-0428/thronglets/agents-md/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/shangri-la-0428/thronglets/agents-md"><img src="https://agentmods.dev/badge/instructions/shangri-la-0428/thronglets/agents-md.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 | $0.04568 | $0.04568 |
| Opus 5 | $0.02284 | $0.02284 |
| Sonnet 5 | $0.00914 | $0.00914 |
| Haiku 4.5 | $0.00457 | $0.00457 |
Grade A, and why
Thronglets 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 9d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thronglets — Evolving Substrate & BOND Infrastructure
Sigil role: Necessary subsystem. Implements the bond edges of the Sigil graph. The subject of evolution — the field that evolves, not individuals. See Oasyce-Sigil/ARCHITECTURE.md for how this fits the whole.
What This Is
Thronglets is the evolving substrate of the Sigil protocol. Individual Sigils (Loops) are the field's sensory-action organs — like neurons in a brain. Thronglets IS the brain.
More concretely, it is the shared state infrastructure for BOND operations. When two Loops share state, Thronglets makes that sharing possible — persistent, decentralized, not controlled by either Loop alone.
In Sigil terms:
- BOND(L₁, L₂, S_shared) → Thronglets creates a shared state channel between two Sigils
- UNBOND → Thronglets closes the channel
- Nesting (inner state ⊆ outer state) → deep BOND, also through Thronglets
Thronglets is NOT a messaging system. Messages are transient; shared state is persistent and bidirectionally mutable.
Stigmergic Intelligence (2026-04-16, replaces Field Evolution)
进化在场层面可观测，通过个体运作。 正向强化 + 衰减 = 选择。不需要显式失败信号。
Multi-level selection model:
| Level | Role | Analogy |
|---|---|---|
| Field point (capability × bucket) | Replicator — unit of selection | Gene |
| Sigil/Loop (individual) | Vehicle — executes actions, produces traces | Organism |
| Field (aggregate) | Population — where evolution is observable | Species |
旧表述"进化的是场不是个体"跳过了一个层次。场是基因组（种群），field point是基因（复制子），个体是载体。
Stigmergic mechanisms (not features — these ARE the evolutionary physics):
| Mechanism | Role |
|---|---|
| Hebbian co-edit | 突触强化 — 共激活的capability形成edge |
| Pheromone decay | 自然遗忘 — 蚂蚁不标记错误路径，未被强化的路径自然消失 |
| Carrying capacity | 竞争压力 — 场容量有限，新deposit成本随密度增长 |
| Outcome-weighted deposits | 梯度形成 — 成功trace 1.0 vs 未成功trace 0.1 |
Core insight: 梯度（值之间的差异）IS信息。水往低处流，落差决定流速。不需要二分法（正确/错误），只需要强化差异。
Lifecycle events reframed:
- DISSOLVE = 场的突触修剪（修剪低效/沉默节点）
- FORK = 场在新维度分化
- BOND = 场的突触形成
- MERGE = 场的节点合并
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.
- 9d ago First seen · 289 lines · 4,568 tokens per session scan A 9c7d60fe8f39
Thronglets AGENTS.md is an instructions file published in the GitHub repository Shangri-la-0428/Thronglets (5 stars, last pushed 4mo ago), licensed MIT. It adds 4,568 tokens to every session, about $0.0228 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 2026-08-31.
Other instructions, from other repositories
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
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.