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.
git clone --depth 1 https://github.com/lokafinnsw/claude-code-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-help)<a href="https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-help"><img src="https://agentmods.dev/badge/commands/lokafinnsw/claude-code-goal-mode/goal-help.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 | $0.00007 | $0.01435 |
| Opus 5 | $0.00003 | $0.00718 |
| Sonnet 5 | $0.00001 | $0.00287 |
| Haiku 4.5 | $0.00001 | $0.00144 |
Grade A, and why
goal-help 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Mode plugin help
v3 Explicit CLI Verbs (recommended workflow)
In v3.0+, the Stop hook is hint-only on lifecycle=pursuing by default. Drive the goal explicitly:
| Command | Purpose |
|---|---|
/goal-mode:goal-current |
Show cursor task + AC coverage |
/goal-mode:goal-evidence-add |
Add evidence for a criterion |
/goal-mode:goal-achieve |
Claim achievement (advances cursor or → review-pending) |
/goal-mode:goal-review-request |
Print reviewer dispatch template |
/goal-mode:goal-submit-verdict |
Record reviewer verdict (GO/NOGO/REVISE) |
/goal-mode:goal-as-builtin |
Emit text for piping into built-in /goal |
Recommended workflow:
/goal-mode:goal-current— see the task.- Do the work in normal Claude Code mode.
- For each AC:
/goal-mode:goal-evidence-add --criterion N --file path[:line] --note "...". /goal-mode:goal-achieve— claim achievement.- If
review-pending:/goal-mode:goal-review-request→ dispatch reviewers viaAgent({subagent_type, prompt})→/goal-mode:goal-submit-verdictper verdict.
Legacy v2 tag-emission workflow remains supported under stopHookDriver: true config (see [docs/MIGRATION-v2-to-v3.md]).
Commands
| Command | Description |
|---|---|
/goal-plan <mission> |
Build a hierarchical plan tree from scratch (LLM bootstrap). Lifecycle → draft. |
/goal-plan-from-file <path> |
Convert an existing Markdown plan file into the goal-mode schema. Lifecycle → draft. Use this when you already have a plan in Markdown. |
/goal-approve-plan |
Validate the draft and lock it. Lifecycle → approved. |
/goal-start [--max-iter N] [--token-budget N] [--time-budget Nm|Nh] [--force] |
Begin pursuing. Lifecycle → pursuing. --force to overwrite an existing active goal. |
/goal-status |
Show plan tree, cursor, budget, last events. |
/goal-tree |
Render the active plan as an ASCII tree with status glyphs (✓/▶/🔵/⛔/·). |
/goal-doctor [--fix] [--json] |
Diagnose health (state/tree, schema, backups, cursor, plugin pin, Stop-hook liveness, budget, event-log, retention). --fix applies safe auto-fixes. --json for machine output. |
/goal-pause |
Lifecycle → paused. Stop hook exits cleanly. |
/goal-resume |
Lifecycle → pursuing (refused if budget exhausted). |
/goal-approve [--reason "..."] |
Manually issue GO for current review-pending node. |
/goal-abandon --reason "..." |
Lifecycle → unmet (refused on terminal lifecycles). |
/goal-clear [--archive] |
Remove active goal directory. PERMANENT — pass --archive to snapshot to .claude/goals/archive/<ts>-<goal_id>/ first. |
/goal-help |
This message. |
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 · 89 lines · 7 tokens per session scan A b6e93687e453
goal-help is a command published in the GitHub repository lokafinnsw/claude-code-goal-mode (3 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 1,435 once invoked, about $0.0000 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.