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-proofgit 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-proof)<a href="https://agentmods.dev/skills/lubluniky/dale/dale-proof"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-proof/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-proof"><img src="https://agentmods.dev/badge/skills/lubluniky/dale/dale-proof.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 | $0.00127 | $0.01530 |
| Opus 5 | $0.00063 | $0.00765 |
| Sonnet 5 | $0.00025 | $0.00306 |
| Haiku 4.5 | $0.00013 | $0.00153 |
Grade A, and why
dale-proof 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 11d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dale Proof
Establish what the available evidence actually proves. Work backward from a technical claim to the shortest decisive observation; never promote source inventory, green secondary checks, or plausible reasoning into runtime truth.
Verify without repairing
- Treat the supplied result as an object to verify, not a request to fix it. Diagnose or implement only when the user separately asks.
- Default to read-only inspection and non-destructive validation. Do not deploy, restart, promote, mutate production data, alter configuration, or perform a real external transaction merely to obtain proof.
- Preserve dirty worktrees and live systems. Never mutate Git, expose secrets, print raw environment values, or capture sensitive payloads.
- Stay in the current task. Do not create Codex tasks, subagents, or review swarms merely to make the verdict look independent.
- Describe same-agent verification honestly. Dale Proof checks evidence but does not provide reviewer independence; use a separately authorized review workflow when independence itself is an acceptance criterion.
- Ask for new authority only when the decisive signal requires a sensitive, destructive, or externally mutating action. Otherwise gather the strongest safe evidence available and bound the verdict accordingly.
Read references/proof-contract.md completely before gathering evidence.
Build the proof
1. Normalize the claim
Preserve the user's original claim before bounding it. Split it into atomic material claims without dropping quantifiers, named environments, side effects, user-visible outcomes, or forbidden outcomes. Map every material phrase from the original claim to an atomic claim or an explicit uncovered obligation. For each atomic claim record:
- exact subject and expected behavior;
- target environment, revision, identity, and time window;
- success and failure observations;
- forbidden side effects;
- strongest available primary signal;
- inaccessible surfaces that limit certainty.
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.
- 11d ago First seen · 162 lines · 127 tokens per session scan A 2d76834fae49
dale-proof is a skill published in the GitHub repository lubluniky/dale (51 stars, last pushed 5d ago), licensed MPL-2.0. It adds 127 tokens to every session and 1,530 once invoked, about $0.0006 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
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
axiom-sre
Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, production debugging, or log investigation.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-self-heal
Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.