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.
git clone --depth 1 https://github.com/markmhendrickson/foundationWrote 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/rules/markmhendrickson/foundation/behavioral_self_adaptation)<a href="https://agentmods.dev/rules/markmhendrickson/foundation/behavioral_self_adaptation"><img src="https://agentmods.dev/badge/rules/markmhendrickson/foundation/behavioral_self_adaptation/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/rules/markmhendrickson/foundation/behavioral_self_adaptation"><img src="https://agentmods.dev/badge/rules/markmhendrickson/foundation/behavioral_self_adaptation.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 | $0.00031 | $0.04190 |
| Opus 5.5 | $0.00012 | $0.01676 |
| Sonnet 5.5 | $0.00006 | $0.00838 |
| Haiku 4.5 | $0.00003 | $0.00419 |
Grade A, and why
behavioral_self_adaptation 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 1mo 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 — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavioral Self-Adaptation Rule
Reference: durable agent rules are authored as Neotoma agent_policy entities
(canonical), never as harness rule files. See Neotoma agent_policy
ent_82b64b6c4104843e43853666. This replaces the former
instruction_documentation.mdc, which named a directory removed in c3255ba and
directed rule-writing into .cursor/rules/ — the opposite of the current policy.
Purpose
Enables agents to learn from user interventions and proactively suggest behavioral improvements. When a user provides guidance that resolves an agent stopping point, the agent analyzes the intervention, identifies generalizable patterns, and suggests appropriate rules, skills, or hooks to prevent similar stops in the future.
Scope
This document defines:
- When agents MUST analyze interventions for patterns
- How to classify intervention types
- How to suggest appropriate artifacts (rules/skills/hooks)
- Integration with existing meta-rules and decision frameworks
This document does NOT cover:
- Explicit instruction capture (see
prompt_integration_rules.mdc) - Risk management hold points (see
risk_management.mdc) - Rule creation standards: Neotoma
agent_policy(ent_82b64b6c4104843e43853666)
Configuration
No additional configuration required. This rule integrates with existing systems:
# Uses existing configuration from:
# - foundation-config.yaml (risk management, agent instructions)
# - docs/prompt_integration_rules.mdc (explicit instruction patterns)
# - Neotoma agent_policy ent_82b64b6c4104843e43853666 (rule authoring location)
Trigger Patterns
Agents MUST analyze for self-adaptation opportunities when:
- After agent stops/pauses and requests user input
- User provides guidance that resolves the stopping point
- Guidance implies pattern beyond one-time instruction
- Pattern is generalizable to future similar circumstances
Detection signals:
- Agent asked a question, user answered with behavioral guidance
- Agent stopped at uncertainty, user clarified decision rule
- Agent completed partial work, user indicated to continue with related work
- Agent requested approval, user indicated future similar cases should proceed automatically
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.
- 1mo ago First seen · 536 lines · 31 tokens per session scan A bd832046a3ed
behavioral_self_adaptation is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 4,190 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.