Borrowing it
Nothing to install: this file belongs to aget-framework/aget. 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/aget-framework/aget/main/.claude/skills/aget-create-goal/SKILL.mdgit clone --depth 1 https://github.com/aget-framework/agetWrote 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/skills/aget-framework/aget/aget-create-goal)<a href="https://agentmods.dev/skills/aget-framework/aget/aget-create-goal"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-create-goal.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 | $0.00123 | $0.01272 |
| Opus 5 | $0.00062 | $0.00636 |
| Sonnet 5 | $0.00025 | $0.00254 |
| Haiku 4.5 | $0.00012 | $0.00127 |
Grade A, and why
aget-create-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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aget-create-goal — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aget-create-goal
Commit a Goal — a durable, named, cross-session outcome (C926) — into governed storage. The singular committer that consumes a /aget-propose-goals candidate; the create-side of the verb pair (L1067 two-propose semantics; L1085 plural-leads-singular).
Enforcement: D71-Strict (CAP-GOAL-008). Once invoked, direct Write/Edit of a committed-Goal section in governance/GOALS.md is PROHIBITED — creation MUST route through this skill, which writes the provenance field that the bypass check reads. Mirrors /aget-create-project and /aget-create-initiative.
Input
<candidate> — a selected /aget-propose-goals candidate, or a goal description. Flags: --aspirational (record to the agent-internal tier instead of committing).
Engine
The falsifiable core is scripts/create_goal.py (11 firing falsifiers in tests/test_create_goal.py, ADR-007). This skill orchestrates it; the script enforces the spec.
Steps
Step 0: Tier decision (REQ-3 two-tier)
- Committed (default): a goal the principal commits to → structured section in
governance/GOALS.md(principal-facing surface), D71-Strict. - Aspirational (
--aspirational): a candidate not yet committed →.aget/goals/aspirational.jsonl(agent-internal), Advisory. Promotion aspirational→committed is a latercreate-goal(committed) act.
Step 1: Conflation guard (CAP-GOAL-002 / C930)
Reject a "goal" defined by workstreams/tasks rather than a measurable end-state. validate_outcome() fires on stream-enumeration with no outcome. If rejected, return the candidate to /aget-propose-project (it is a project, not a goal).
Step 2: Required fields
type∈ {Achieve, Maintain, Soft} (CAP-GOAL-003)≥1 loop⟨owner, trigger, review-action, consequence, cadence⟩ at creation (CAP-GOAL-004 / MP#12) — a Goal without a loop is an orphan that decays. The skill REFUSES to commit a loop-less Goal.parent(Theme/Initiative) where one exists (CAP-GOAL-001)status: activeset at creation (CAP-GOAL-011)
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.
- 7d ago First seen · 66 lines · 123 tokens per session scan A 20fb0a395297
aget-create-goal is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 1,272 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
aget-close-project
Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…
aget-release-critique
Adversarial review with the Critic perspective of the Release Delivery Triad (L818). Dual-mandate: spec coverage audit + deep bug finding.
aget-release-audit-specs
Audit specifications with the Spec Auditor perspective of the Release Delivery Triad (L818). Coverage and consistency mode.
aget-release-build
Execute gate deliverables with the Builder perspective of the Release Delivery Triad (L818). Speed-optimized execution mode.
aget-file-issue
File issues with L520 governance compliance.
aget-propose-actions
Propose ranked next-best actions with evidence grounding, time budgets, and execute-all default. Formalizes the fleet's highest-frequency interaction pattern.