Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/sbhooley/ainativelang/continuitygit clone --depth 1 https://github.com/sbhooley/ainativelangWhat 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 | $0.00000 | $0.00983 |
| Opus 5 | $0.00000 | $0.00491 |
| Sonnet 5 | $0.00000 | $0.00197 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
continuity 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Continuity Guide
This project is intentionally designed for multi-session, multi-agent development. Use this guide to continue work safely and efficiently across handoffs.
Primary Goal
Preserve correctness of AINL language/runtime behavior while improving model quality on strict canonical AINL generation.
First-Read Checklist (Every New Session)
- If you will do implementation work: Read
docs/BOT_ONBOARDING.mdand complete the steps indocs/OPENCLAW_IMPLEMENTATION_PREFLIGHT.mdbefore coding (seetooling/bot_bootstrap.json). - Read
README.mdanddocs/DOCS_INDEX.md. - Read
docs/AINL_SPEC.mdandSEMANTICS.md. - Read
docs/RUNTIME_COMPILER_CONTRACT.md(compiler/runtime + grammar ownership contract). - Read
docs/TRAINING_ALIGNMENT_RUNBOOK.mdbefore touching train/eval scripts. - Read
docs/DOCS_MAINTENANCE.mdbefore broad documentation edits. - Read latest reports:
corpus/curated/alignment_run_health.jsoncorpus/curated/model_eval_trends.json
- Inspect current generation quality report:
corpus/curated/model_eval_report_v5_aligned.json(or latest variant)
- If planning an integration or major change, review consultant reports:
agent_reports/AI_CONSULTANT_REPORT_APOLLO.md— OpenClawocladapter integration strategydocs/ZEROCLAW_INTEGRATION.md— ZeroClaw skill + MCP bootstrap (parallel integration path)
- Operator / field narratives (what shipped in live stacks):
agent_reports/README.md— indexed OpenClaw agent field reports (e.g. Day 2 AINL King, 2026-03-19). - Intelligence monitors (memory / bootstrap / summarizer AINL):
docs/INTELLIGENCE_PROGRAMS.mdandscripts/run_intelligence.py.
Ground Rules for Safe Progress
- Do not weaken strict AINL validation just to improve score.
- Do not patch runtime to hide compiler-analysis gaps; fix compiler-owned contract logic.
- Prefer additive changes (new flags/diagnostics) over breaking behavior.
- Keep constrained decoding deterministic for eval comparability.
- Preserve machine-readable artifacts in
corpus/curated/. - If adding optimization knobs, wire them through:
- script CLI
- cycle script
- output diagnostics
- docs
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.
- 2d ago First seen · 99 lines · 0 tokens per session scan A 789b78ed3365
continuity is an agent published in the GitHub repository sbhooley/ainativelang (671 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 983 tokens. 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 2026-08-30.
Other agents, from other repositories
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.