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-lensesgit 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-lenses)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-lenses"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-lenses/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-lenses"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-lenses.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 | $0.00135 | $0.01265 |
| Opus 5 | $0.00068 | $0.00633 |
| Sonnet 5 | $0.00027 | $0.00253 |
| Haiku 4.5 | $0.00014 | $0.00127 |
Grade A, and why
dale-lenses 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 12d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dale Lenses
Change the representation of a hard problem before changing the answer. Apply a specific epistemic method with an observable artifact and a stop rule; never simulate rigor by naming several frameworks and repeating the same opinion.
Keep the method bounded
- Preserve the user's current phase. Analyze, decide, plan, or implement only to the extent requested; invoking a lens does not authorize execution.
- Require a bounded question. When the user is still discovering the goal, options, taste, or priorities, keep or move the conversation to ordinary brainstorming instead of imposing a lens prematurely.
- Stay in the current task. Do not create Codex tasks or subagents merely to manufacture perspectives. Use tools only when actual evidence is needed and already authorized.
- Separate observations, inferences, assumptions, preferences, and unknowns.
- Redact secrets, credentials, raw environment values, personal data, private transaction identifiers, and other sensitive operational evidence before it enters a tool call, artifact, or response.
- Select one primary lens. Add one challenging lens only when it makes a materially different prediction, exposes a different failure mode, or could reverse the decision.
- Honor a lens named by the user. If it does not fit the problem, explain the mismatch briefly and offer the closest fitting lens instead of silently substituting it.
- Decline the method when ordinary reasoning is sufficient. “No useful reframe” is better than framework theatre.
Select by problem signature
Read references/lens-contracts.md completely before applying a lens.
| Lens | Use when the core uncertainty concerns | Required artifact |
|---|---|---|
causal |
competing explanations or interventions | rival causal models and a discriminating observation |
systems |
feedback, delays, recurrence, or second-order effects | bounded feedback model with testable predictions |
temporal |
retries, ordering, concurrency, TTL, or version skew | state transitions and a concrete interleaving trace |
conservation |
missing or duplicated money, events, jobs, inventory, or authority | scoped balance equation and residual |
invert |
consequential failure paths or ineffective safeguards | minimal failure recipe, controls, and tripwires |
constraint |
throughput stays flat despite local optimization | evidenced system constraint and migration signal |
contradiction |
two necessary requirements appear mutually exclusive | exact coupling and a separation that tests both sides |
decide |
costly choice under uncertainty or irreversibility | options, states, regret, reversibility, and value of information |
What ships with it
2 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.
- 12d ago First seen · 117 lines · 135 tokens per session scan A 69d9e310416f
dale-lenses is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 6d ago), licensed MPL-2.0. It adds 135 tokens to every session and 1,265 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
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…