Agent skill

Echoes Vault

by psinetron in psinetron/echoes-vault-codex

Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime.

MITAuto-check passedAgent Workflows

Install Echoes Vault

skills CLI
$ npx skills add psinetron/echoes-vault-codex --skill echoes-vault -a claude-code

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

GitHub CLI
$ gh skill install psinetron/echoes-vault-codex echoes-vault --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/psinetron/echoes-vault-codex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/echoes-vault .claude/skills/echoes-vault && 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
echoes-vault
GitHub stars
131
Token cost
~1.1k tokens
SKILL.md length
450 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime.

  • Works in 8 steps: Read before writing. Search the vault… → Store dry technical facts, decisions,… → Start every page with YAML frontmatter… → …
  • The user asks Codex to remember
  • SKILL.md covers Core rules, Choose an operation and Successful completion
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Echoes Vault is an agent skill from psinetron/echoes-vault-codex. Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime. Use when the user asks Codex to remember, record, log, search, recall, document, or update project knowledge; when work depends on earlier architectural decisions; or after a meaningful sub-task should survive across agents and sessions. Do not use it for final distillation unless the user explicitly requests echoes-end.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Agent memory. The repository describes itself as: Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions. The licence is MIT.

When your agent uses it

  • The user asks Codex to remember
  • Update project knowledge
  • Work depends on earlier architectural decisions
  • After a meaningful sub-task should survive across agents and sessions

Example prompts

  • “/echoes-vault”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Read before writing. Search the vault and read an existing page before updating it.
  2. Store dry technical facts, decisions, contracts, configurations, verified fixes, blockers, and next steps—not chat transcripts.
  3. Start every page with YAML frontmatter containing type, stack, and status.
  4. Include summary: a non-empty single line of at most 160 characters describing the page.
  5. Never edit index.md; the CLI generates it deterministically from page filenames, summary,
  6. Use [[wikilinks]] for page references and ![[asset.png]] for files in EchoesVault/assets/.
  7. Deprecate instead of deleting. Set status: deprecated, prepend > [!warning] DEPRECATED,
  8. Never report final memory as saved after normal task completion. Only $echoes-end may finalize a session.

What it can do on your machine

Read from SKILL.md and the folder at commit 0b8ff17. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

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

  • Network

    No URLs in SKILL.md.

    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

Echoes Vault loads about 1.1k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 450 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 psinetron/echoes-vault-codex at commit 0b8ff17, republished under its MIT licence (© psinetron). 450 words, ~1,050 tokens.

Download SKILL.mdSave it as .claude/skills/echoes-vault/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
echoes-vault
description
Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime. Use when the user asks Codex to remember, record, log, search, recall, document, or update project knowledge; when work depends on earlier architectural decisions; or after a meaningful sub-task should survive across agents and sessions. Do not use it for final distillation unless the user explicitly requests echoes-end.

EchoesVault memory operations

Keep durable project knowledge in <workspace>/EchoesVault/. Resolve <workspace> as the Git root when one exists, otherwise the current working directory. Resolve <plugin-root> as the parent of the skills/ directory that contains this SKILL.md. Use <plugin-root>/scripts/echoes_vault.py as <launcher>. It delegates execution to a compatible project runtime, recovers a missing runtime for an initialized vault, refuses an outdated runtime until explicit upgrade, and never downgrades a newer one.

Run the deterministic storage CLI with:

text
python3 <launcher> --workspace <workspace> \
  --agent codex --adapter-version 1.1.1 <command>

Pass write payloads as JSON through stdin (--payload -) or a temporary JSON file. Do not interpolate untrusted Markdown into a shell command.

Core rules

  1. Read before writing. Search the vault and read an existing page before updating it.
  2. Store dry technical facts, decisions, contracts, configurations, verified fixes, blockers, and next steps—not chat transcripts.
  3. Start every page with YAML frontmatter containing type, stack, and status.
  4. Include summary: a non-empty single line of at most 160 characters describing the page.
  5. Never edit index.md; the CLI generates it deterministically from page filenames, summary, and status without loading page bodies into model context.
  6. Use [[wikilinks]] for page references and ![[asset.png]] for files in EchoesVault/assets/.
  7. Deprecate instead of deleting. Set status: deprecated, prepend > [!warning] DEPRECATED, and link to the replacement.
  8. Never report final memory as saved after normal task completion. Only $echoes-end may finalize a session.

Choose an operation

Recall before work

Use targeted search when an existing component, decision, API, schema, or configuration might already be documented:

text
python3 <launcher> --workspace <workspace> \
  --agent codex --adapter-version 1.1.1 search "specific keyword"

Read the returned page around each relevant line. Follow replacement links from deprecated pages.

Show full SKILL.md (190 more words)Show less
Append an intermediate note

After a verified logical unit, an architectural agreement, a context switch, or an explicit “remember/log this” request, submit:

json
{
  "entry": "- Implemented X.\n- Verified with Y.\n- Remaining blocker: Z.",
  "agent": "codex"
}

to append --payload -. Keep the entry concise. This is a scratchpad write and does not end the session.

If no vault exists and the user has asked to remember something, run init first. Otherwise, do not initialize a vault implicitly.

Create or update a knowledge page

Use a page for a durable global concept such as an architecture, API contract, schema, library integration, hardware mapping, or ADR.

For a new page, submit to upsert --payload -:

json
{
  "filename": "auth-architecture.md",
  "content": "---\ntype: architecture\nstack: [python]\nstatus: active\nsummary: Authentication boundaries and token flow.\n---\n\n# Authentication architecture\n"
}

For an existing page:

  1. Read the full page.
  2. Run hash <filename> and copy its sha256.
  3. Submit the full replacement content plus expectedSha256 to upsert.

Retain or deliberately update the page's summary when replacing its full content. The optimistic hash prevents overwriting a concurrent edit in the current checkout. If it fails, reread the page and reconcile changes. A project-level runtime lock serializes simultaneous EchoesVault writers.

Successful completion

Confirm the exact session-entry or page path written. Mention whether the generated index changed. Keep working unless the user requested a final save.

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

Files

SKILL.md and 1 other file in skills/echoes-vault of psinetron/echoes-vault-codex.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0b8ff17

Compare with similar skills

Echoes Vault 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.

Echoes Vault compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Echoes Vault this skillpsinetron/echoes-vault-codex131—~1.1kAutomated safety check: PassMIT
Coding Agent Session Findercode-yeongyu/oh-my-openagent70k1 repos~2.8kAutomated safety check: PassCustom licence
Claude-Mem Cloud Syncthedotmack/claude-mem98k1 repos~1kAutomated safety check: NotesApache-2.0
Cognee CLI Memory Commandstopoteretes/cognee32k1 repos~2.2kAutomated safety check: NotesApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Claude-Mem Searchthedotmack/claude-mem98k1 repos~511Automated safety check: PassApache-2.0

Similar skills

  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub starsUsed in 1 repo~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude-Mem Cloud Sync

    thedotmack/claude-mem

    Checks claude-mem cloud sync status and guides you through connecting a cmem.ai Pro account without the sync token ever passing through the chat.

    98k GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes
  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub starsUsed in 1 repo~2.2k tokens
    Agent WorkflowsAuto-check: notes
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Claude-Mem Search

    thedotmack/claude-mem

    Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.

    98k GitHub starsUsed in 1 repo~511 tokens
    Agent WorkflowsAuto-check passed
  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from psinetron/echoes-vault-codex

  • Echoes End

    psinetron/echoes-vault-codex

    Explicitly finalize an EchoesVault session by distilling the current conversation into a dense daily summary and durable knowledge pages, then regenerating the deterministic index.

    131 GitHub stars~665 tokensUpdated 1 mo ago
    Auto-check passed
  • Echoes Init

    psinetron/echoes-vault-codex

    Initialize, migrate, or repair the agent-neutral EchoesVault structure, portable runtime, and Codex/OpenCode/Claude adapters for the current project.

    131 GitHub stars~631 tokensUpdated 1 mo ago
    Auto-check passed
  • Echoes Status

    psinetron/echoes-vault-codex

    Show a compact EchoesVault status card and report protocol, adapter, storage, metadata, index, conflict, and scalability health.

    131 GitHub stars~596 tokensUpdated 1 mo ago
    Auto-check passed
  • Echoes Start

    psinetron/echoes-vault-codex

    Start an EchoesVault working session by restoring the generated page index and the three most recent session entries.

    131 GitHub stars~408 tokensUpdated 1 mo ago
    Auto-check passed
  • Echoes Vault

    psinetron/echoes-vault-codex

    Use repository-local EchoesVault memory when asked to initialize, restore, search, remember, document, inspect status, or explicitly save a session.

    131 GitHub stars~263 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Echoes Vault

What does Echoes Vault do?

Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime. Echoes Vault is an agent skill from psinetron/echoes-vault-codex. Maintain agent-neutral, repository-local project memory through the portable EchoesVault runtime.

When should I use Echoes Vault?

Echoes Vault fits situations like: the user asks Codex to remember; update project knowledge; work depends on earlier architectural decisions; after a meaningful sub-task should survive across agents and sessions.

How do I install Echoes Vault in Claude Code?

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

How do I install Echoes Vault in Codex?

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

Can I use Echoes Vault 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 psinetron/echoes-vault-codex --skill echoes-vault -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/echoes-vault, .gemini/skills/echoes-vault, .github/skills/echoes-vault and .opencode/skills/echoes-vault in your project.

What does Echoes Vault need to run?

SKILL.md names no scripts, command-line tools or credentials: Echoes Vault is instructions for the agent only. Our summary lists: Python 3.

Does Echoes Vault access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Echoes Vault 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 Echoes Vault use?

Echoes Vault 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 Echoes Vault use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Echoes Vault?

Skills that share tags, products or a category with Echoes Vault: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Claude-Mem Cloud Sync (thedotmack/claude-mem, 98k stars), Cognee CLI Memory Commands (topoteretes/cognee, 32k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Echoes Vault?

psinetron (a GitHub user) maintains it in psinetron/echoes-vault-codex, which has 131 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 4, 2026.

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