Obelisk

What it does

When your agent uses it

• Asks how did I fix X
• What did we do last time
• Find the session where
• References past work you lack context for

Example prompts

• “how did I fix X”
• “what did we do last time”
• “find the session where”
• “/obelisk”

Requirements

• Pre-approved tools (allowed-tools): Read, Bash(obelisk:*), Write

Workflow steps

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

1. 1Choose the narrowest project, file, session, time range, or topic scope.
2. 2Normally start a new task with overview({ limit: 6 }); skip orientation
3. 3Recall prior conclusions with memories() and verify against session
4. 4Group, deduplicate, and project inside the query. Return stable IDs and short
5. 5Answer with concise evidence. Identify prior memories naturally when they

What it can do on your machine

Read from SKILL.md and the folder at commit a4b7329. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash(obelisk:*)
  • Write

  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 bash).

  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

Obelisk loads about 1.6k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 165 tokens; SKILL.md has 622 words of instructions outside code blocks.

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

~165

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

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~25k

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 tommy0103/obelisk at commit a4b7329, republished under its AGPL-3.0 licence (© tommy0103). 622 words, ~1,550 tokens.

name

obelisk

description

Search and query past Claude Code, Codex, Kimi Code, Kiro, OMP, and Pi session history. Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录". Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response. Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.

allowed-tools

Read, Bash(obelisk:*), Write

qdir=$(mktemp -d /tmp/obq.XXXXXX 2>/dev/null || { d="/tmp/obq.$$.$RANDOM"; mkdir "$d"; echo "$d"; })
qfile="$qdir/query.mjs"
cat > "$qfile" <<'JS'
const hits = search('auth fix', { limit: 5 });
return hits.map(h => ({
  session_id: h.session.id, uuid: h.message.uuid,
  content_type: h.message.content_type,
  snippet: h.message.text?.slice(0, 240),
}));
JS
obelisk --query "$qfile"

obelisk --search "keyword" --nonce "obq-<unique-token-you-invent>"

© tommy0103, AGPL-3.0. 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 20 other files (references) in skill-doc of tommy0103/obelisk.

• SKILL.md
• references/advanced-helpers.md
• references/api-reference.md
• references/memory-workflow.md
• references/pitfalls.md
• references/query-patterns.md
• references/recap-patterns.md
• references/recap-writing.md
• references/recap/overview.md
• references/recap/pattern1-cover.md
• references/recap/pattern2-thinking.md
• references/recap/pattern3-vibe.md
• references/recap/pattern4-workflow.md
• references/recap/pattern5-closing.md
• references/recap/writing1-cover.md
• references/recap/writing2-thinking.md
• references/recap/writing3-vibe.md
• references/recap/writing4-workflow.md
• references/recap/writing5-closing.md
• … and 2 more

Open the folder on GitHubat commit a4b7329