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-loopgit 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)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-loop"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop/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"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-loop.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 | $0.00041 | $0.00590 |
| Opus 5 | $0.00020 | $0.00295 |
| Sonnet 5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
dale-loop 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dale Loop
Use observe -> decide -> act -> verify -> persist -> wait or stop.
Choose the smallest loop that fits the work; do not force a PR pipeline.
Define the contract
Infer the outcome, observation source, trigger or cadence, allowed actions, direct verifier, durable state, user resource limits, and terminal condition. Ask only for missing information that changes the outcome or authority. Keep existing user authorization; a skill invocation does not authorize unrelated publication, merging, deployment, or messages.
Choose a focused mode when useful:
$dale-loop-project: several independently deliverable PRs.$dale-loop-pr: one existing PR through review or repair.$dale-loop-repo: recurring repository maintenance.$dale-loop-watch: meaningful-change monitoring.$dale-loop-goal: one sustained objective.
Execute and resume
During an active run, use subagents for independently useful work and inherited model settings. Give each a concrete output, exclusive write scope or read-only scope, verifier, and no further delegation. Keep overlapping mutations sequential. Do complementary work while workers run. Separate user-owned Codex tasks require an explicit request for separate tasks; they are not the default work unit.
For future wakeups, use the product's automation mechanism. Persist source and artifact identities, completed actions, failed signals, and the next condition in the automation prompt or an authorized durable artifact. Do not assume a subagent or its conversation survives a wakeup. Re-observe before resuming and avoid duplicate actions against unchanged state.
Use a goal mechanism only for an explicitly requested goal, within its live schema; do not fabricate a token budget. Cadence belongs to automations, not a blocking shell sleep. Stay quiet on unchanged or non-actionable wakes unless the user requested periodic reports. Notify on meaningful change or required action.
Verify against the actual source, checkout, PR head, or runtime. Agent completion text alone is insufficient. After repeated unchanged failure, change approach; stop at a real blocker, terminal condition, or user limit. Disable completed scheduled work through the supported automation tool; archive the user task only when requested.
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.
- 2d ago Changed · -1 lines · -18 tokens per session d620adac5d17
- 10d ago First seen · 63 lines · 59 tokens per session scan A 6266bff5ef6a
dale-loop is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 3d ago), licensed MPL-2.0. It adds 41 tokens to every session and 590 once invoked, about $0.0002 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
agent-creation-skill
Procedural guide for creating new agents from templates when project complexity requires delegation.
memory-fabric
Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting. Unifies search results ranked by recency, relevance, and authority. Use when designing memory retrieval, building entity graphs, or optimizing knowledge graph…
loop-graph
Compile one durable loop-graph run into executor, ledger, directives, ops, and supervisor artifacts under a dated .longgraph directory, then present copy-ready host prompts. Use directly for a custom multi-round shape with gated milestones, independent audit, cross-host execution, or durable state; focused sibling…
longgraph
Route and author durable long-horizon loop-graph runs. Use for multi-round work needing durable state, gated milestones, owner boundaries, host switching, or independent audit. Route code cleanup to /loop-converge, feature requirements to /loop-deliver, and evidence-backed solution comparison to /loop-research; use…
loop-converge
Author and optionally direct-launch a two-node loop-graph run whose North Star is code convergence — delete unused code, merge duplicates, reuse, slim. Use when the user invokes /loop-converge, or asks to loop on dead code, duplication, unused exports, DRY cleanup, or merging twin implementations. Starts the owner…
loop-deliver
Author and optionally direct-launch a two-node loop-graph run for implementing a product or engineering requirement through verified vertical slices. Use when a requested feature, integration, migration, or behavior change needs multiple rounds, durable acceptance proof, and independent audit. Not for code cleanup…