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.
npx skills add lubluniky/dale --skill dale-loop-goalgit clone --depth 1 https://github.com/lubluniky/daleWrote 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/lubluniky/dale/dale-loop-goal)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-loop-goal"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop-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/lubluniky/dale/dale-loop-goal"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop-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 | $0.00036 | $0.00304 |
| Opus 5.5 | $0.00014 | $0.00122 |
| Sonnet 5.5 | $0.00007 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
dale-loop-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 1mo 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
Dale Loop Goal
Keep one objective coherent across work and resumptions. State the completion predicate and current evidence, then take the smallest useful next action. Use subagents only when independent work emerges; inherit model settings and keep a single coordinator. Do not turn sequential work into a swarm.
Use the goal tool only when a goal was explicitly requested. Follow its live status and blocking rules; set a token budget only if the user supplied one. For a requested later wakeup, use an automation instead of a blocking sleep. Persist enough state to re-observe the actual target before the next action.
Continue through authorized work. Ask for missing authority or a consequential choice only when needed and finish unaffected work meanwhile. When the same failure repeats without new evidence, change approach rather than retry harder. Honor user limits and the goal tool's exact completion/blocking semantics.
Finish with the outcome, direct evidence, and any actual unmet condition.
Cancellation and changed scope
On cancellation or revoked scope, interrupt affected workers immediately before other work, invalidate pending outputs, and preserve existing changes. Update or disable related scheduled work only within the user's cancellation scope. For a correction, stop conflicting work first, then send the revised contract; accept subsequent results only against the current request and artifact state.
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.
- 1mo ago Changed · +10 lines · -15 tokens per session 2d7ae44848ec
- 1mo ago First seen · 22 lines · 51 tokens per session scan A 132817de7d09
dale-loop-goal is a skill published in the GitHub repository lubluniky/dale (54 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 36 tokens to every session and 304 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 2026-08-30.
Other skills, from other repositories
loop-graph
Use only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.
loop-research
Use only when the user explicitly invokes /loop-research or names this skill. Authors a loop-research run. Do not use unless named. Do not execute or resume generated runtime node files.
longgraph
Use only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.
loop-converge
Use only when the user explicitly invokes /loop-converge or names this skill. Authors a loop-converge run. Do not use unless named. Do not execute or resume generated runtime node files.
loop-deliver
Use only when the user explicitly invokes /loop-deliver or names this skill. Authors a loop-deliver run. Do not use unless named. Do not execute or resume generated runtime node files.
atelier
Atelier design intelligence (El DT + Impeccable). Use for UI/UX design, craft, critique, audit, polish, anti-slop, tokens, decks, and frontend iteration. Invoke /atelier [target]. Covers landing, dashboard, product UI, components, motion, a11y, and design system alignment.