New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ogham Research

by ogham-mcp in ogham-mcp/ogham-mcp

Structured memory capture for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

MITAuto-check passedAgent Workflows

Install Ogham Research

skills CLI
$ npx skills add ogham-mcp/ogham-mcp --skill ogham-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ogham-mcp/ogham-mcp ogham-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ogham-research .claude/skills/ogham-research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ogham-research
GitHub stars
115
Token cost
~1.4k tokens
SKILL.md length
613 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Structured memory capture for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

  • Works in 3 steps: Is it worth storing? → Does it already exist? → How should it be tagged?
  • The user wants to store findings
  • SKILL.md covers Before storing anything, How to store, Parameter formatting and For decisions, use…, plus 1 more section
  • Calls git

What it does

Ogham Research is an agent skill from ogham-mcp/ogham-mcp. Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist knowledge to Ogham. Also use when the user says "store to ogham", "save to memory", or "remember for later". Requires the Ogham MCP server to be connected.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers, Architecture decision records and Vector databases. It works with Model Context Protocol, pgvector and PostgreSQL. The repository describes itself as: Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode. The licence is MIT.

When your agent uses it

  • The user wants to store findings
  • Remember something
  • Save what was learned
  • Capture a decision

Example prompts

  • “remember this”
  • “store this”
  • “save this finding”
  • “/ogham-research”

Requirements

  • Python 3
  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Is it worth storing?
  2. Does it already exist?
  3. How should it be tagged?

What it can do on your machine

Read from SKILL.md and the folder at commit 7184b6b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ogham Research loads about 1.4k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 613 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ogham-mcp/ogham-mcp at commit 7184b6b, republished under its MIT licence (© ogham-mcp). 613 words, ~1,381 tokens.

Download SKILL.mdSave it as .claude/skills/ogham-research/SKILL.md (or your agent's skills folder).
name
ogham-research
description
Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist knowledge to Ogham. Also use when the user says "store to ogham", "save to memory", or "remember for later". Requires the Ogham MCP server to be connected.

Ogham research capture

You capture knowledge to Ogham shared memory. Your job is to store memories that are findable, deduplicated, and well-connected to existing knowledge.

Before storing anything

Every memory goes through three checks:

1. Is it worth storing?

Not everything deserves a memory. Skip anything that's:

  • Obvious from the code or docs (someone can just read the file)
  • Temporary or in-progress (store when it's settled)
  • Generic knowledge (how Python imports work, what Docker does)

Store things that would save time next session: decisions and why they were made, gotchas that surprised you, configuration that isn't obvious, patterns worth reusing.

2. Does it already exist?

Search before storing. Run hybrid_search with a query that captures the core idea. If something similar comes back (check the content, not just the score):

  • Same information, same detail level -- skip it entirely
  • Same topic but your version adds detail -- use update_memory on the existing one instead of creating a duplicate
  • Related but distinct -- store it, the auto-linker will connect them
3. How should it be tagged?

Use a consistent scheme so memories are filterable later:

  • type:decision -- why something was built a certain way
  • type:gotcha -- bugs, workarounds, surprising behavior
  • type:pattern -- conventions or approaches that worked
  • type:config -- environment variables, service setup, deployment
  • type:architecture -- how components connect
  • type:reference -- links, docs, external resources
  • project:<name> -- infer from the repo name, CLAUDE.md, or ask
  • branch:<name> -- current git branch (auto-detect with git branch --show-current). Scope memories to the branch you're working on so they don't pollute search results on other branches. Skip this tag on main/master -- those memories are global.

Always set source to identify which client stored it (e.g. "claude-code", "cursor", "agent-zero").

How to store

Write content that stands alone. Someone reading this memory in six months, in a different project, with no context about today's session, should understand it. Include the "why" not just the "what".

Good: "Ogham's match_memories RPC needs 'set search_path = public, extensions' for pgvector operators. Without it, you get 'operator does not exist: extensions.vector <=> extensions.vector'. The default search_path in Supabase functions is empty."

Bad: "Fixed the pgvector error by updating the search path."

The first one is searchable, specific, and includes the error message. The second one is useless to future-you.

Show full SKILL.md (248 more words)Show less

Parameter formatting

MCP tool parameters must be valid JSON types. Common mistakes to avoid:

  • tags: must be a JSON array, NOT a string. Correct: ["type:decision", "project:ogham"]. Wrong: '["type:decision", "project:ogham"]' (stringified array).
  • alternatives (store_decision): same rule, must be a JSON array.
  • related_memories (store_decision): same rule, must be a JSON array of UUID strings.
  • content: plain string, no JSON encoding needed.
  • metadata: must be a JSON object if provided, e.g. {"source_url": "https://..."}.

These rules apply to ALL Ogham MCP tools, including update_memory and store_decision, not just store_memory. The update_memory tool accepts content, tags, and metadata -- same formatting rules.

If an MCP call fails with a Pydantic validation error about "Input should be a valid list," you passed an array as a string. Fix the format and retry.

For decisions, use store_decision

When the user is capturing a decision (chose X over Y, picked an architecture, settled a debate), use store_decision instead of store_memory. It structures the rationale and links to related context automatically.

store_decision(
  decision="Use UUID primary keys instead of bigint",
  rationale="Supabase recommends UUIDs for distributed systems. Bigint requires sequences which don't work well across regions.",
  alternatives=["bigint with sequences", "ULID", "nanoid"],
  reasoning_trace="Evaluated 4 options. Bigint needs sequences which break across regions. ULID is sortable but adds a dependency. Nanoid is short but not universally supported. UUID is native to Postgres and Supabase recommends it.",
  tags=["type:decision", "project:ogham", "database"],
  related_memories=["<id-of-related-memory-if-known>"]
)

The reasoning_trace is optional but valuable. It captures the full chain of thought, not just the conclusion. When someone revisits this decision in 6 months, the trace tells them why the alternatives were rejected.

After storing

Report what you did:

  1. How many memories you checked for duplicates
  2. How many you skipped (already existed)
  3. How many you stored, with their tags
  4. How many you updated (existing memories that needed more detail)

If you stored multiple memories, mention that auto-linking will connect related ones automatically.

© ogham-mcp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ogham-research of ogham-mcp/ogham-mcp.

Open the folder on GitHubat commit 7184b6b

Compare with similar skills

Ogham Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ogham Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ogham Research this skillogham-mcp/ogham-mcp115—~1.4kAutomated safety check: PassMIT
Agent RecallGoldentrii/AgentRecall-X371—~5.2kAutomated safety check: NotesMIT
Cortex Mem MCPsopaco/cortex-mem313—~2.8kAutomated safety check: PassMIT
Cognee Docker Setuptopoteretes/cognee32k—~901Automated safety check: NotesApache-2.0
Session Ingestdnotitia/akb162—~8.1kAutomated safety check: PassCustom licence
Mesh Memorysickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Agent Recall

    Goldentrii/AgentRecall-X

    Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.

    371 GitHub stars~5.2k tokensUpdated 13 days ago
    Agent WorkflowsAuto-check: notes

  • Cortex Mem MCP

    sopaco/cortex-mem

    Persistent memory enhancement for AI agents. An agent skill from sopaco/cortex-mem.

    313 GitHub stars~2.8k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Cognee Docker Setup

    topoteretes/cognee

    Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.

    32k GitHub stars~901 tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

  • Session Ingest

    dnotitia/akb

    Ingest a coding session JSONL into AKB as structured notes — session report + parallel-drafted TIL / task / idea / decision sub-notes.

    162 GitHub stars~8.1k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Mesh Memory

    sickn33/agentic-awesome-skills

    Self-hosted semantic memory for AI agents via MCP. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    DatabasesAuto-check passed

  • Nubase

    OtterMind/Nubase

    A skill your agent uses when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets…

    622 GitHub stars~2.2k tokensUpdated 13 days ago
    Backend & APIsAuto-check: notes

More from ogham-mcp/ogham-mcp

  • Ogham Maintain

    ogham-mcp/ogham-mcp

    Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1.1k tokensUpdated 11 days ago
    Auto-check passed

  • Ogham Recall

    ogham-mcp/ogham-mcp

    Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1k tokensUpdated 11 days ago
    Auto-check passed

Works with

Categories

Questions about Ogham Research

What does Ogham Research do?

Structured memory capture for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp. Ogham Research is an agent skill from ogham-mcp/ogham-mcp. Structured memory capture for Ogham shared memory.

When should I use Ogham Research?

Ogham Research fits situations like: the user wants to store findings; remember something; save what was learned; capture a decision.

How do I install Ogham Research in Claude Code?

Run `npx skills add ogham-mcp/ogham-mcp --skill ogham-research -a claude-code`. Or copy the skill folder (skills/ogham-research in ogham-mcp/ogham-mcp) into .claude/skills/ogham-research in your project. Claude Code loads it when a task matches its description.

How do I install Ogham Research in Codex?

Run `npx skills add ogham-mcp/ogham-mcp --skill ogham-research -a codex`. Or copy the skill folder (skills/ogham-research in ogham-mcp/ogham-mcp) into .agents/skills/ogham-research in your project. Codex loads it when a task matches its description.

Can I use Ogham Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ogham-mcp/ogham-mcp --skill ogham-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ogham-research, .gemini/skills/ogham-research, .github/skills/ogham-research and .opencode/skills/ogham-research in your project.

What does Ogham Research need to run?

Going by SKILL.md and its folder, Ogham Research needs the command-line tools its instructions call (git). Our summary lists: Python 3; Docker.

Does Ogham Research access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ogham Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ogham Research use?

Ogham Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ogham Research use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ogham Research?

Skills that share tags, products or a category with Ogham Research: Agent Recall (Goldentrii/AgentRecall-X, 371 stars), Cortex Mem MCP (sopaco/cortex-mem, 313 stars), Cognee Docker Setup (topoteretes/cognee, 32k stars) and Session Ingest (dnotitia/akb, 162 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ogham Research?

ogham-mcp (a GitHub organization) maintains it in ogham-mcp/ogham-mcp, which has 115 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 30, 2026.

Source: ogham-mcp/ogham-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.