How do I install the Okf Agent Memory skill?

Run npx skillmds@latest add okf-memory/okf-agent-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Okf Agent Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Okf Agent Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Okf Agent Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Okf Agent Memory?

okf-memory (@okf-memory) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Okf Agent Memory by okf-memory — Agent Skill

Name: Okf Agent Memory
Rating: 4.666666666666667 (3 reviews)
Author: okf-memory

Okf Agent Memory

Maintain persistent, domain-neutral project memory for AI agents using Open Knowledge Format (OKF) v0.2 bundles and the deterministic okf Go toolchain. Use whenever project knowledge, decisions, runbooks, research, client notes, or domain discoveries must survive conversational resets.

okf-memory Updated Sep 22, 2026

File contents

OKF Agent Memory Skill (AAG Spec v0.1)

Teaches AI agents deterministic interaction with an Open Knowledge Format (OKF v0.2) bundle (knowledge/).

0. Project & Domain Codex

GOAL: maintain(high_factual_integrity, domain_neutrality, strict_determinism)
FORMAT: diagrams => ASSERT(syntax == mermaid, ELSE=STOP("Mermaid required; ASCII/box art prohibited."))

1. Behavioral Invariants (RFC 2119)

MUST execute okf_search(query=keywords, limit=3) before proposing architecture changes or creating concepts.
NEVER scan knowledge/ via list_dir, grep_search, or raw file readers.
NEVER forge human verification (verified: is human-only; declare generated: { by: "<actor>", at: "<iso-time>" }).
PREFER native okf_* MCP tools OVER CLI fallback commands.
PREFER okf_update OVER okf_create when mutating existing domain entities.
NEVER persist scratchpads, raw chain-of-thought, or speculative chatter to knowledge corpus.

2. Guard Clauses & Scope Governance

ON edit(@path/): IF first_visit(@path/) => okf_search(for_path=@path/) IF governance == "hold" => STOP("Subsystem frozen by governance. Confirm with user.") IF governance == "constraint" => MUST adhere to all listed invariants IF governance == "context" => proceed with awareness
ON user_query(architecture | requirements | conventions | domain_facts): okf_search(query=keywords, limit=3) => evaluate summary description IF relevant => okf_show(concept_id) ONLY on demand

3. Completion Pipeline (Sequential Assertion Gates)

IF arch_decisions_made => MUST okf_create(architecture/*, type="decision", title=..., desc=...)
IF requirements_discovered => MUST okf_update(concept_id)
IF concepts_mutated => MUST sync(knowledge/log.md, knowledge/index.md)
ASSERT(okf_validate(strict=true, drift=true) == {errors: 0, warnings: 0}, ELSE=fix_before_exit)

4. Tooling Reference (Dual-Mode: MCP & CLI)

Default bundle: ./knowledge. For custom paths, pass bundle="path/to/bundle".

Task	Preferred: Native MCP Tool	Fallback: Deterministic CLI (`--json`)
Search Knowledge	`okf_search(query="<query>", limit=3)`	`okf search "<query>" knowledge --limit 3 --json`
Discover Code Constraints	`okf_search(for_path="<file-path>")`	`okf search --for-path <file-path> knowledge --json`
Inspect Concept	`okf_show(concept_id="<id>")`	`okf show <id> knowledge --json`
Create Concept	`okf_create(concept_id="<id>", type="<type>", title="<title>", description="<desc>")`	`okf create <id> knowledge --type <type> --title "<title>" --desc "<desc>" --json`
Update Concept	`okf_update(concept_id="<id>", description="<desc>", title="<title>")`	`okf update <id> knowledge --desc "<desc>" --json`
Relate Concepts	`okf_relate(source_id="<src>", target_id="<tgt>", description="<prose>")`	`okf relate <src> <tgt> knowledge --desc "<prose>" --json`
Validate Bundle	`okf_validate(strict=true)`	`okf validate knowledge --strict --drift --json`

5. Workflow Guides (Progressive Disclosure)

Discovery & Retrieval: discovery.md
Persistence Decisions: remember.md
Updating & Mutations: update.md
Relationship Topology: relationships.md
Multi-Domain Reference: examples.md

---name: okf-agent-memorydescription: Maintain persistent, domain-neutral project memory for AI agents using Open Knowledge Format (OKF) v0.2 bundles and the deterministic okf Go toolchain. Use whenever project knowledge, decisions, runbooks, research, client notes, or domain discoveries must survive conversational resets.---# OKF Agent Memory Skill (AAG Spec v0.1)Teaches AI agents deterministic interaction with an Open Knowledge Format (OKF v0.2) bundle (`knowledge/`).## 0. Project & Domain Codex- GOAL: maintain(high_factual_integrity, domain_neutrality, strict_determinism)- FORMAT: diagrams => ASSERT(syntax == mermaid, ELSE=STOP("Mermaid required; ASCII/box art prohibited."))## 1. Behavioral Invariants (RFC 2119)- MUST execute `okf_search(query=keywords, limit=3)` before proposing architecture changes or creating concepts.- NEVER scan `knowledge/` via `list_dir`, `grep_search`, or raw file readers.- NEVER forge human verification (`verified:` is human-only; declare `generated: { by: "<actor>", at: "<iso-time>" }`).- PREFER native `okf_*` MCP tools OVER CLI fallback commands.- PREFER `okf_update` OVER `okf_create` when mutating existing domain entities.- NEVER persist scratchpads, raw chain-of-thought, or speculative chatter to knowledge corpus.## 2. Guard Clauses & Scope Governance- ON edit(@path/): IF first_visit(@path/) => okf_search(for_path=@path/) IF governance == "hold" => STOP("Subsystem frozen by governance. Confirm with user.") IF governance == "constraint" => MUST adhere to all listed invariants IF governance == "context" => proceed with awareness- ON user_query(architecture | requirements | conventions | domain_facts): okf_search(query=keywords, limit=3) => evaluate summary description IF relevant => okf_show(concept_id) ONLY on demand## 3. Completion Pipeline (Sequential Assertion Gates)1. IF arch_decisions_made => MUST okf_create(architecture/*, type="decision", title=..., desc=...)2. IF requirements_discovered => MUST okf_update(concept_id)3. IF concepts_mutated => MUST sync(knowledge/log.md, knowledge/index.md)4. ASSERT(okf_validate(strict=true, drift=true) == {errors: 0, warnings: 0}, ELSE=fix_before_exit)---## 4. Tooling Reference (Dual-Mode: MCP & CLI)Default bundle: `./knowledge`. For custom paths, pass `bundle="path/to/bundle"`.| Task | Preferred: Native MCP Tool | Fallback: Deterministic CLI (`--json`) || :--- | :--- | :--- || **Search Knowledge** | `okf_search(query="<query>", limit=3)` | `okf search "<query>" knowledge --limit 3 --json` || **Discover Code Constraints** | `okf_search(for_path="<file-path>")` | `okf search --for-path <file-path> knowledge --json` || **Inspect Concept** | `okf_show(concept_id="<id>")` | `okf show <id> knowledge --json` || **Create Concept** | `okf_create(concept_id="<id>", type="<type>", title="<title>", description="<desc>")` | `okf create <id> knowledge --type <type> --title "<title>" --desc "<desc>" --json` || **Update Concept** | `okf_update(concept_id="<id>", description="<desc>", title="<title>")` | `okf update <id> knowledge --desc "<desc>" --json` || **Relate Concepts** | `okf_relate(source_id="<src>", target_id="<tgt>", description="<prose>")` | `okf relate <src> <tgt> knowledge --desc "<prose>" --json` || **Validate Bundle** | `okf_validate(strict=true)` | `okf validate knowledge --strict --drift --json` |---## 5. Workflow Guides (Progressive Disclosure)- Discovery & Retrieval: [discovery.md](./discovery.md)- Persistence Decisions: [remember.md](./remember.md)- Updating & Mutations: [update.md](./update.md)- Relationship Topology: [relationships.md](./relationships.md)- Multi-Domain Reference: [examples.md](./examples.md)

Frequently asked questions