Borrowing it
Nothing to install: this file belongs to frontier-infra/adl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frontier-infra/adl/main/.claude/commands/goal.mdgit clone --depth 1 https://github.com/frontier-infra/adlWrote 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/frontier-infra/adl/goal)<a href="https://agentmods.dev/commands/frontier-infra/adl/goal"><img src="https://agentmods.dev/badge/commands/frontier-infra/adl/goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/frontier-infra/adl/goal"><img src="https://agentmods.dev/badge/commands/frontier-infra/adl/goal.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00015 | $0.00852 |
| Opus 5.5 | $0.00006 | $0.00341 |
| Sonnet 5.5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
goal 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a new /goal contract. The manifest you write becomes the binding success criterion for whatever work follows. Workers cannot report done until Warden verifies against this manifest and writes a sign-off proof.
What to do
-
Pick a task-id. Format:
YYYYMMDD-<slug>-<4hex>. Slug is 2-5 words from the goal, kebab-case. Hex is 4 random characters to disambiguate. -
Resolve the role and project. Based on the goal text and
.claude/orchestrator/ARGENT.mdrouting rules, decide which role (forge/quill/scout) will execute the slice and which project overlay applies. If either is unclear, ask the operator. Do not guess. -
Translate the goal into machine checks. For each thing the operator implied, write one
done_whenentry. Prefertestandcommandchecks. Fall back tofile_exists/file_containsfor documentation slices. Usehuman_reviewonly when the goal is genuinely subjective (Scout findings, design decisions) — and then state explicitly what the reviewer should confirm. -
Add diff constraints when scope matters. If the operator named specific files, populate
diff_constraint.touches_only. If files must not be touched (auth, billing, schema migrations are common), populateforbidden. Skip both for documentation-only slices. -
Write the manifest to
.claude/goals/<task-id>.yaml. Create the directory if it does not exist. -
Surface the manifest back to the operator before dispatching anything. If a
done_whencheck is fuzzy ("works correctly," "is fast enough"), say so and ask the operator to tighten it. A vague manifest is worse than no manifest — it gives Warden license to rubber-stamp.
Manifest schema
id: <task-id>
created: <ISO-8601>
operator: <operator name or '@me'>
slice: <one-line description>
role: forge | quill | scout
project: <PROJECT_*.md or 'none'>
base_ref: <git ref to diff against, default: HEAD>
goal: <imperative sentence — what 'done' looks like>
done_when:
- name: <human-readable check name>
type: test | command | file_exists | file_contains | diff_constraint | human_review
# type-specific fields below
# test:
command: <test-runner command>
expect_pass: true
# command:
command: <shell command>
expect_exit: 0
# file_exists:
path: <path>
# file_contains:
path: <path>
pattern: <regex or literal>
# diff_constraint:
touches_only: [<glob>, ...]
forbidden: [<glob>, ...]
# human_review:
description: <what the reviewer is confirming>
constraints: # optional — non-negotiable rules carried from project overlay
- <one-liner>
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.
- 2mo ago First seen · 69 lines · 15 tokens per session scan A 1126e85a8211
goal is a command published in the GitHub repository frontier-infra/adl (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 852 once invoked, about $0.0001 per session on Opus 5.5. 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
dashboard-session-diff
Show file changes (git diff) for a session by id-prefix. Usage /dashboard:session-diff . Runs locally, no LLM.
dashboard-session-unhide
Unhide a previously hidden session. Usage /dashboard:session-unhide.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
resolve-dependabot-prs
Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.