Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add lokafinnsw/claude-code-goal-mode/plugin install goal-modeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-start)<a href="https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-start"><img src="https://agentmods.dev/badge/commands/lokafinnsw/claude-code-goal-mode/goal-start.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00269 |
| Opus 5 | $0.00009 | $0.00134 |
| Sonnet 5 | $0.00004 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
goal-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Goal Start
The user invoked /goal-start with possibly some flags after. Parse them from the user's message. Defaults if not given:
--max-iter→200--token-budget→5000000--time-budget→4h--force→ only if explicitly typed
Run via Bash (replace placeholders with parsed values):
"${CLAUDE_PLUGIN_ROOT}/scripts/start-goal.sh" --max-iter <N> --token-budget <N> --time-budget <Nh-or-Nm> [--force]
If the script returns ❌ goal already active (lifecycle=pursuing, ...); use --force to restart, ask the user whether to restart with --force (warning: this clears progress).
The Stop hook is now active. Tell the user the cursor + budget summary the script printed, then begin work on the cursor task immediately.
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.
- 8d ago First seen · 25 lines · 18 tokens per session scan A 475636b199dc
goal-start is a command published in the GitHub repository lokafinnsw/claude-code-goal-mode (3 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 269 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.
Other commands, from other repositories
upgrade
Comprehensive dependency upgrade with security audit, prioritization, and validation.
from-spec
Extract Architecture Decision Records from a completed spec.
push
Validate and push commits with lint, type, and build checks.
pop
Pop an item off the stash and continue working on it in the current session.
drop
Drop a stash item without working on it.
push
Push an idea onto the stash to handle later.