start

A command for starting a Seeks work session, which is an organized attempt to achieve a coding goal. It can restart a finished session or update one whose base branch has changed.

In plain words
What is it for?
Use it to start the newest or a named Seeks loop, check whether its base branch is current, and recreate its working folder when a finished or outdated loop needs to run again.
Why use it?
It makes sure the session starts from an appropriate version of the code and warns you before refreshing work based on newer changes.

Command

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.

agentmods
npx agentmods add commands/bogzx/seeks/start
Clone the repo
git clone --depth 1 https://github.com/Bogzx/seeks
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00978
Opus 5 $0.00013 $0.00489
Sonnet 5 $0.00005 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured yesterday against content hash 1c835d405e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 yesterday.

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.

commands/start.md · 18 lines

What it actually says

Run shell via the Bash tool; never bare-cd (use git -C / subshells / absolute paths).

  1. Pick the loop (<name>). If no name was given → node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" latest (the most-recently-touched loop); if that prints nothing, tell the user there are no loops (/seeks:new <goal> first) and STOP. Otherwise <name> = $0. Tell the user which loop you're starting.
  2. Freshness check (re-run / stale base). Read node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" status-get <name> and node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" base-check <name>. If the loop's done is true (you're re-running a finished loop) OR base-check prints moved (the base branch advanced since this loop was set up), ask the user once (default yes): "Base <base_ref> has moved / this loop already finished — refresh it against the latest code before running? (recommended)". On yes:
    • Finished loop → fresh re-scaffold from the latest base (keep the recipe): node … gc <name> (removes the old worktree+branch+run — keeps spec.md); re-create git worktree add .claude/worktrees/<name> -b seeks/<name> "<base_ref>"; re-analyze the blast radius and rewrite .seeks/run/<name>/context.md; node … init <name> '{…fresh status from spec.md — armed:false, done:false, verifier_certified:false, dry_sweeps:0, no_progress_count:0, base_ref, worktree_path, the spec's min_dry_sweeps/max_iters/thresholds…}'; node … base-record <name>; backlog-add the starter items from spec.md; reconcile open_items; write a fresh state.md.
    • In-progress loop, base moved → rebase + re-analyze (keep the work): git -C .claude/worktrees/<name> rebase "<base_ref>" (on conflict, STOP and tell the user to resolve); rewrite context.md; node … base-record <name>. On no, continue without refreshing.
  3. node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" lock-acquire <name> — if it exits non-zero, the loop is running elsewhere (fresh heartbeat). STOP and tell the user.
  4. Reset sticky guards + the iteration counter so a paused/halted loop resumes with a fresh budget: node … status-set <name> '{"armed":true,"needs_human":false,"no_progress_count":0}' then node … reset-fires <name> (this also clears the gate's release latch — a loop that already finished/halted wakes up again). If it previously halted on max-iters, ask the user whether to raise max_iters first.
    • Time budget. If the user passed --for <dur> / --until <time>, convert it to seconds and run node … budget-set <name> <sec>. Then always stamp the clock so the wall-clock budget counts from this start: node … start-clock <name>. (Absent any budget, this is a no-op for termination — the loop runs as before.)
    • Maker model nudge: read node … role maker and tell the user one line — "this loop's tier runs the maker best on <model>; you drive the maker yourself, so /model <model> to match (or carry on)." The maker is this session, so seeks can't switch it for you.
  5. Call the EnterWorktree tool with path: ".claude/worktrees/<name>".
  6. Begin exactly the first pass per the /seeks:loop skill (read it now), then STOP — end your turn after that single pass. Do NOT continue into the next pass. End the pass with progress-tick, then stop. The Stop hook re-invokes you for each subsequent pass and sustains the loop until done / needs-human / stuck / max_iters.
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. yesterday First seen · 18 lines · 26 tokens per session scan A 1c835d405e74

Subscribe to this mod's changes

start is a command published in the GitHub repository Bogzx/seeks (4 stars, last pushed 15d ago), licensed MIT. It adds 26 tokens to every session and 978 once invoked, about $0.0001 per session on Opus 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.