Borrowing it
Nothing to install: this file belongs to arcasilesgroup/ai-engineering. 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/arcasilesgroup/ai-engineering/main/.agents/skills/ai-goal/SKILL.mdgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-goal)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-goal"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-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/skills/arcasilesgroup/ai-engineering/ai-goal"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.01382 |
| Opus 5 | $0.00069 | $0.00691 |
| Sonnet 5 | $0.00028 | $0.00276 |
| Haiku 4.5 | $0.00014 | $0.00138 |
Grade A, and why
ai-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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One run, no mid-run stop
/ai-goal <goal> is the person saying "this one runs without me". The whole cycle runs
in one pass and the person comes back only when there is a finished thing to test. The
invocation is the standing approval; you never ask again, and you never claim an approval
you did not earn.
What it produces
The finished thing handed to the person: the change committed at HEAD, the
ai-eng audit verify gate output shown in full, and the acceptance checklist the person
runs against the real artifact.
The order
Read policy/skill-sequence.toml and follow it; if that file is absent, refuse to
continue — the order is data, not prose. Load each stage's own skill and follow it:
/ai-research, /ai-spec, /ai-challenge, /ai-council, /ai-build, /ai-review,
/ai-verify, /ai-security, the audit verb, then /ai-ship.
Tiers, per the repository's pin
Each stage runs on the tier the repository's [models] section configures — never a
model name coded into this skill, and never a provider the repository did not choose.
Ask the tier the stage deserves, matching model_router's own mapping: research and
spec run on the low tier, security, review, plan and audit on the top tier, and
build, verify, ship (and everything the pin leaves untiered) on medium, falling back
to default_tier when a tier is not configured. The command event records which model
the pin says each verb routes to (tier_model) and what the surface actually ran
(model); the two are different facts and the run never conflates them.
Tools are whatever the client has
The cycle uses only the tools present on this machine: the local floor (the repository,
the IDE and the assigned surface, the ai-eng harness, the model available) is always on,
and a web provider or NotebookLM is used only when the client configured it. An absent tool
degrades the stage that would use it — the research stage names degraded-tool: <name>
and carries on with the local floor. Nothing in this skill depends on a tool the client
does not have.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 106 lines · 139 tokens per session scan A dbeb4c3220f0
ai-goal is a skill published in the GitHub repository arcasilesgroup/ai-engineering (54 stars, last pushed yesterday), licensed Apache-2.0. It adds 139 tokens to every session and 1,382 once invoked, about $0.0007 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…