Borrowing it
Nothing to install: this file belongs to billbai-longarena/Termite-Protocol. 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/billbai-longarena/Termite-Protocol/main/CLAUDE.mdgit clone --depth 1 https://github.com/billbai-longarena/Termite-ProtocolWrote 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/billbai-longarena/termite-protocol/claude-md)<a href="https://agentmods.dev/instructions/billbai-longarena/termite-protocol/claude-md"><img src="https://agentmods.dev/badge/instructions/billbai-longarena/termite-protocol/claude-md.svg" alt="Measured on agentmods" 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 | $0.05341 | $0.05341 |
| Opus 5 | $0.02670 | $0.02670 |
| Sonnet 5 | $0.01068 | $0.01068 |
| Haiku 4.5 | $0.00534 | $0.00534 |
Grade C, and why
Termite-Protocol CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
7. ~~`field-export-audit.sh` `cp -R` creates nested `signals/signals/` directory~~ **FIXED** — added `rm -rf` before `cp -R` to prevent nesting when target exists (cross-colony signal: ReactArmor O-003) How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Termite Protocol — Source Repository
This is the 协议源仓库 (protocol source repo) for the Termite Protocol (白蚁协议), a cross-session collaboration framework for stateless AI agents.
This is NOT a 宿主项目 (host project). This is the protocol source repo itself. Your work here evolves the protocol spec and field scripts that all host project colonies depend on.
Terminology (权威术语表)
| 中文 | English | Meaning |
|---|---|---|
| 白蚁协议 | Termite Protocol | The framework as a whole (generic reference only) |
| 协议规范 | protocol spec | The TERMITE_PROTOCOL.md document and its 10+4 rules |
| 协议源仓库 | protocol source repo | This Git repo (billbai-longarena/Termite-Protocol) |
| 宿主项目 | host project | Any project that installed the protocol via install.sh |
| 蚁丘 | colony | The runtime signal ecosystem (signals/ + rules/ + .pheromone + .birth) inside a host project |
| 协议模板 | protocol template(s) | Files in /templates/ that get copied to host projects |
| 反馈回路 | feedback loop | Colony → audit package → protocol source repo → Nurse → template fix → host project upgrade |
Repository Map
templates/
TERMITE_PROTOCOL.md ← Canonical protocol spec (v5.1). Changes here propagate to all host projects on next upgrade.
CLAUDE.md / AGENTS.md ← Entry file templates installed into host projects.
TERMITE_SEED.md ← Minimal protocol payload injected into generated agent systems.
UPGRADE_NOTES.md ← Structured changelog with per-version changes and action items for host projects.
scripts/
field-lib.sh ← Shared function library (path resolution, YAML parsing, signal I/O, DB bridge)
field-arrive.sh ← Agent arrival: reads environment + protocol, computes .birth file
field-cycle.sh ← Heartbeat: sense → act → notice → deposit
field-deposit.sh ← Pheromone deposition (observations/decisions → YAML signals)
field-decay.sh ← Pheromone decay (expire stale signals)
field-drain.sh ← Bulk signal clearing
field-pulse.sh ← Project status snapshot
field-claim.sh ← Atomic task lock/release/query
field-genesis.sh ← Self-initialization for new colonies
field-export-audit.sh ← Export audit packages (protocol artifacts only, no source code)
field-migrate.sh ← Signal migration: upgrade pre-v5.0 observations (quality_score + source_type)
field-submit-audit.sh ← Submit audit packages as PRs to this repo
termite-db.sh ← SQLite WAL-mode database + migrations
hooks/ ← Git hooks (pre-commit, pre-push, prepare-commit-msg, post-commit)
install.sh ← One-click installer for host projects (copies protocol templates, creates dirs, installs hooks, prints upgrade summary)
0227/ ← Production reference colony (SalesTouch). Contains live signals, observations, and rules from real usage.
audit-packages/ ← Cross-colony audit data submitted from host projects.
audit-analysis/ ← Analysis reports and optimization proposals derived from audit data.
docs/plans/ ← Design documents for major features.
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 First seen · 182 lines · 5,341 tokens per session scan C 56455cd6dcbc
Termite-Protocol CLAUDE.md is an instructions file published in the GitHub repository billbai-longarena/Termite-Protocol (11 stars, last pushed 7d ago), licensed MIT. It adds 5,341 tokens to every session, about $0.0267 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.