manage-local-knowledge

manage-local-knowledge is a skill for Codex from luutru433-coder/local-knowledge-suite. It costs 85 tokens per session (976 once invoked), scanned A, original, MIT.

A workflow for setting up and using reusable local knowledge across Windows projects. It can keep project memory separate from company information and route different kinds of knowledge to their designated storage.

In plain words
What is it for?
Starting memory-only projects, connecting projects to a company repository, choosing global or project-local installation, restoring or migrating knowledge, and checking project identity and access.
Why use it?
It helps prevent one project’s knowledge, company facts, or identity from being confused with another’s, while supporting safe setup and migration.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Good fit Starting memory-only projects, connecting projects to a company repository, choosing global or project-local installation, restoring or migrating knowledge, and checking project identity and access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge
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 luutru433-coder/local-knowledge-suite --skill manage-local-knowledge
Clone the repo
git clone --depth 1 https://github.com/luutru433-coder/local-knowledge-suite

Made for: 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-local-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge/github.svg)](https://agentmods.dev/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge)
Your own site
<a href="https://agentmods.dev/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge"><img src="https://agentmods.dev/badge/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge/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-local-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge"><img src="https://agentmods.dev/badge/skills/luutru433-coder/local-knowledge-suite/manage-local-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 976 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 $0.00085 $0.00976
Opus 5.5 $0.00034 $0.00390
Sonnet 5.5 $0.00017 $0.00195
Haiku 4.5 $0.00009 $0.00098

Measured 1mo ago against content hash 8c066d8e241c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

manage-local-knowledge 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.

plugins/local-knowledge-suite/skills/manage-local-knowledge/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage Local Knowledge

Use the plugin-owned runtime with an absolute Windows project root. Never infer a project or company path from the skill directory, import a target project's knowledge code, or guess a missing identity.

Read references/windows-setup.md for setup, cloning, migration, installation modes, and snapshots. Read references/collected-skill-summary.md when interpreting storage ownership or tool results.

Preserve trust boundaries

  • Treat Skills as instructions, not remembered context or factual evidence.
  • Treat Memory as preferences, decisions, corrections, commitments, entities, and conventions for exactly one project.
  • Treat company facts as evidence only after the citation gate passes.
  • Treat a company-enabled project manifest as identity, not authorization. Normal company access also requires the machine-local project_id + canonical root + company_id enrollment created by explicit bootstrap or restore.

Route advanced Memory maintenance to $memorizer. Route company ingestion, review, portal, user, publication, and Git operations to $company-knowledge-base.

Bootstrap or restore

  1. Resolve the intended project root to an absolute path.
  2. Call knowledge_status(root) before mutation.
  3. If no manifest exists, call bootstrap_workspace(root, company_id=None, profile="memory-only", install_mode="global") unless the user explicitly chooses another profile. Tell the user to review and commit the project manifest and managed .gitignore additions in their application repository.
  4. Require a registered company ID for combined or company-only. Never create a company implicitly during bootstrap or recall.
  5. If migration is required, stop normal writes. Preview and apply the supported migration; never edit schema numbers manually.
  6. After clone, run project restore; register and re-ingest company sources when applicable; verify vendored files; then run project doctor.

Read the full file on GitHub · 100 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 100 lines · 85 tokens per session scan A 8c066d8e241c

Subscribe to this mod's changes

manage-local-knowledge is a skill published in the GitHub repository luutru433-coder/local-knowledge-suite (0 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 976 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

douyin-favorites-to-knowledge

A tool for copying videos saved in an authorised Douyin account into a local Markdown or Obsidian knowledge base. Douyin is a Chinese short-video platform, and Obsidian is an app for organising linked notes.

tars1230/douyin-favorites-to-knowledge · 92 tokens

fkf-learn

Keep FKF project notes, wiki concepts and task folders current after meaningful work. Use after a decision, a finished task, a corrected assumption, or when the user asks to remember something.

fmind/fkf · 43 tokens

fkf-maintain

Maintain FKF bases - collector health, scheduled updates, backfills, validation and retrieval cases. Use when fkf status reports stale or failing sources, when adding a collector, or when setting up a schedule.

fmind/fkf · 47 tokens

douyin-favorites-to-knowledge

A workflow for syncing videos saved or liked by an authorised Douyin account into local Markdown files or an Obsidian knowledge base, a folder of linked research notes.

tars1230/douyin-favorites-to-knowledge · 92 tokens

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…

mem0ai/mem0 · 146 tokens

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

mem0ai/mem0 · 47 tokens