manage-okf-memory

manage-okf-memory is a skill for Claude Code, Codex from tsnAnh/flutter-agentic-starter. It costs 69 tokens per session (442 once invoked), scanned A, original, MIT.

A project memory manager for the OKF format, which stores durable project knowledge in Markdown files. It organizes coding patterns, requirements, decisions, major changes, roadmap items, and daily work notes.

In plain words
What is it for?
Use it at the start and end of work to read project context, create daily logs, merge older notes into base knowledge, and record decisions or reusable coding guidance.
Why use it?
It keeps important context available between work sessions instead of leaving it scattered in temporary notes or conversations. It also separates lasting knowledge from short-lived debugging details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it at the start and end of work to read project context, create daily logs, merge older notes into base knowledge, and record decisions or reusable coding guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tsnanh/flutter-agentic-starter/manage-okf-memory
Install

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.

Any agent
npx skills add tsnAnh/flutter-agentic-starter --skill manage-okf-memory
Clone the repo
git clone --depth 1 https://github.com/tsnAnh/flutter-agentic-starter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for manage-okf-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/tsnanh/flutter-agentic-starter/manage-okf-memory/github.svg)](https://agentmods.dev/skills/tsnanh/flutter-agentic-starter/manage-okf-memory)
Your own site
<a href="https://agentmods.dev/skills/tsnanh/flutter-agentic-starter/manage-okf-memory"><img src="https://agentmods.dev/badge/skills/tsnanh/flutter-agentic-starter/manage-okf-memory/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.

agentmods 80×15 button for manage-okf-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/tsnanh/flutter-agentic-starter/manage-okf-memory"><img src="https://agentmods.dev/badge/skills/tsnanh/flutter-agentic-starter/manage-okf-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00442
Opus 5 $0.00034 $0.00221
Sonnet 5 $0.00014 $0.00088
Haiku 4.5 $0.00007 $0.00044

Measured 8d ago against content hash d2f04a862f4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

manage-okf-memory 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 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.

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.

.agents/skills/manage-okf-memory/SKILL.md · 41 lines

What it actually says

Manage OKF Memory

Use okf-memory/ as the source of truth. Keep it OKF v0.1 compatible: markdown files, YAML frontmatter on concept files, index.md and log.md reserved.

Start Of Work

  1. Run date +%F.
  2. Read okf-memory/index.md, relevant okf-memory/base/*.md, and today's okf-memory/daily/YYYY-MM-DD.md if it exists.
  3. Create today's daily file if no daily file exists.
  4. If the latest okf-memory/daily/*.md file is not today, roll over before other edits.

Rollover

For each prior daily file with merged: false:

  1. Move durable entries into the matching base file: coding-patterns, human-style, project-requirements, decision-changes, major-changes, roadmap.
  2. Deduplicate against existing base facts. Do not preserve transient debugging notes.
  3. Set the daily file to merged: true.
  4. Update changed base files with timestamp and merged_through.
  5. Append a dated entry to okf-memory/log.md.
  6. Create today's daily file with the same sections and merged: false if it does not exist.

End Of Work

Update today's daily file only when there are new durable facts:

  • Coding patterns agents should repeat.
  • Human communication or report style preferences.
  • Stable project requirements or verification rules.
  • Accepted, rejected, or superseded decisions.
  • Major repository changes.
  • Roadmap changes.

Skip repeated facts, speculative ideas, temporary build logs, local paths with private values, secrets, tokens, credentials, and environment values. Put unresolved questions last.

Changes

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.

  1. 8d ago First seen · 41 lines · 69 tokens per session scan A d2f04a862f4b

Subscribe to this mod's changes

manage-okf-memory is a skill published in the GitHub repository tsnAnh/flutter-agentic-starter (7 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 442 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

codify-lesson

Detect recurring P2/P3 audit patterns across recent rounds and promote them into lesson cards. Use after round boundaries or when repeated findings appear.

Arch1eSUN/Arcgentic · 33 tokens

cross-session-handoff

Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.

Arch1eSUN/Arcgentic · 31 tokens

proactive-agent

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.

MerkyorLynn/Lynn · 46 tokens

memory-recall

Persistent cross-session memory system with fact extraction, semantic search, and compiled memory layers. Your agent remembers everything across sessions — user preferences, project context, past decisions, personal details. Use when: (1) User references something from a previous conversation, (2) Agent needs project…

MerkyorLynn/Lynn · 104 tokens

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

task-agent-eliza-bridge

Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.

elizaOS/eliza · 55 tokens