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 dikamilo/dx-workflow --skill dx-distillgit clone --depth 1 https://github.com/dikamilo/dx-workflowWrote 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/dikamilo/dx-workflow/dx-distill)<a href="https://agentmods.dev/skills/dikamilo/dx-workflow/dx-distill"><img src="https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-distill/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/dikamilo/dx-workflow/dx-distill"><img src="https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-distill.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 | $0.00034 | $0.01602 |
| Opus 5.5 | $0.00014 | $0.00641 |
| Sonnet 5.5 | $0.00007 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
dx-distill 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dx-distill
Establish the context later skills would otherwise guess at. Help the user make the decision in front of them, then record its basis — scope, rules, open risks — as context/foundation/briefs/<slug>.md, where every claim carries its source. dx-brainstorm decides whether one idea is worth building; this establishes or refreshes the ground it stands on.
Writes that file and stops. It creates no container and promotes nothing — dx-new stays the router.
Never invent research, user behaviour, quotes, or measurements. A missing fact stays unknown or becomes a named hypothesis. A human's choice to build on an untested assumption doesn't convert it into evidence; a decision with no recorded confirmer stays proposal. Material the current decision actually needs goes on the collection plan — an irrelevant empty section needs no research task.
Guards. context/foundation/ absent → say to run /dx-init, stop. No user available → stop; this is a conversation, and the appetite, constraints and experience it exists to ask about are exactly what you must not invent. Every path named must resolve; an unresolvable one is asked about, never guessed at. An existing <slug>.md is a refresh: keep its ids and its history — a changed decision gets a superseding row, it doesn't overwrite the old one.
1 — Frame the decision, and the emphasis with it
Read enough to state what this session should help decide. Unclear → ask what the brief is for; a brief written toward no decision is a filing exercise, and its sections will be padded to look complete.
In the same exchange, name the emphasis you infer from what the material actually is — the way type already activates plan characteristics without the user naming a mode:
- code and compatibility references → weight
[PRODUCT]; follow up on what stays unchanged, what data is touched, what rollout risks - a client's or stakeholder's material → weight
[INTERVIEW]/[DOCUMENT]; follow up on constraints, integrations, and asks that conflict with each other - another product's own documentation → weight
[BENCHMARK], which supports what that product does and never that we need it - this project's own settled records — a past change,
DESIGN.md, an archived decision → weight[DOCUMENT]; follow up on what was already decided and shouldn't be relitigated - a bare internal idea → weight
[ASSUMPTION]; follow up on the alternatives, the assumption to test, and what would send you back
What ships with it
3 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.
- 1mo ago First seen · 76 lines · 34 tokens per session scan A 5ae12395f818
dx-distill is a skill published in the GitHub repository dikamilo/dx-workflow (8 stars, last pushed 23d ago), licensed MIT. It adds 34 tokens to every session and 1,602 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 2026-09-25.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).