Echoes End

What it does

When your agent uses it

• Save the session to EchoesVault
• Explicitly invokes echoes-end
• Merely because an ordinary task finished

Example prompts

• “/echoes-end”

Requirements

• Python 3

Workflow steps

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

1. 1Distill final outcomes, verified fixes, decisions, unresolved blockers, and concrete next steps. Do not write a transcript.
2. 2Treat scratchpad notes already written today as supporting context; do not duplicate them verbatim.
3. 3Search and read relevant existing pages before proposing page changes.
4. 4For every existing page update, run hash after reading it and include the returned sha256 as expectedSha256.
5. 5Prefer deprecation plus a replacement page over deleting historical documentation.
6. 6Give every new or updated page a non-empty, single-line summary of at most 160 characters.

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 End loads about 665 tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~93

When it runs · the whole SKILL.md, loaded when a task matches

~665

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

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). 262 words, ~665 tokens.

name

echoes-end

description

Explicitly finalize an EchoesVault session by distilling the current conversation into a dense daily summary and durable knowledge pages, then regenerating the deterministic index. Use only when the user asks to end, wrap up, finalize, or save the session to EchoesVault, or explicitly invokes echoes-end. Never trigger merely because an ordinary task finished.

python3 <launcher> --workspace <workspace> \
  --agent codex --adapter-version 1.1.1 end \
  --confirm-explicit-user-end --payload -

{
  "dailySummary": "## Outcomes\n- ...\n\n## Next steps\n- ...",
  "agent": "codex",
  "pages": [
    {
      "filename": "decision-name.md",
      "content": "---\ntype: decision\nstack: [codex]\nstatus: active\nsummary: The decision and its consequences.\n---\n\n# Decision\n..."
    }
  ]
}

© 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-end of psinetron/echoes-vault-codex.

• SKILL.md
• agents/openai.yaml

Open the folder on GitHubat commit 0b8ff17