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-maxgit 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-max)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-max"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-max/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-max"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-max.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 | $0.00036 | $0.00733 |
| Opus 5 | $0.00018 | $0.00367 |
| Sonnet 5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
dale-max 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dale Max
Use a high-assurance review loop for explicitly requested consequential work. The calling agent owns the plan, integration, and final gate. Use subagents for independent implementation or review; separate Codex tasks are optional only when the user explicitly requests them.
Establish the acceptance contract
Define the outcome, authority, criteria, exact target, direct evidence, and material failure modes. Respect user-specified resource limits. Do not impose unlimited review or a fixed number of reviewers. Read contracts.md for worker and reviewer contracts. Default to inherited model and effort; read model-routing.md only for an explicit routing choice.
Implement and review
The coordinator may implement directly or assign a bounded worker with exclusive write scope. Use live collaboration tools and capacity. Workers do not spawn more agents or separate tasks. Keep overlapping writes sequential and preserve unrelated changes. Reuse the implementer for focused revisions.
Run a fresh independent reviewer against the original requirement, raw artifact, and evidence, without the implementer's intended verdict. Delegate distinct review questions only when each covers a material failure mode that could change acceptance. A separate preflight review is useful for costly or hard-to-reverse plans; do not require it for every cycle. The coordinator performs complementary work while review runs.
If independent review is unavailable, continue implementation and direct checks that remain useful, but report the Max independence gate as unavailable. Do not claim a same-agent review is independent or issue final PASS without the gate.
Accept or revise
Resolve findings by direct evidence, target identity, freshness, and coverage. Keep a compact criterion-to-evidence record. Integrate accepted changes and run required checks plus sufficient behavioral validation in the destination. An isolated worker's success does not prove delivery.
What ships with it
4 files 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.
- 3d ago Changed · -139 lines · -60 tokens per session a70e30caccd3
- 11d ago First seen · 216 lines · 96 tokens per session scan A 1b21c28ccf99
dale-max is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 5d ago), licensed MPL-2.0. It adds 36 tokens to every session and 733 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…