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 agentmods add skills/tallesborges/zdx/releasenpx skills add tallesborges/zdx --skill releasegit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/release)<a href="https://agentmods.dev/skills/tallesborges/zdx/release"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/release.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.01180 |
| Opus 5 | $0.00032 | $0.00590 |
| Sonnet 5 | $0.00013 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release zdx
zdx releases are manual and intentional — cut one when a set of features/fixes is ready, not on every commit. The mechanical build+publish lives in .github/workflows/release.yml (workflow_dispatch only). This skill is the human-facing flow that wraps it: pick a version, write a changelog, dispatch, verify.
Source of truth
- Version: root
Cargo.toml→[workspace.package] version. All crates inherit it viaversion.workspace = true, andzdx --versionreports it (clap readsCARGO_PKG_VERSION). Bump it in this one place. - Tag convention:
v<version>(e.g. version0.4.0→ tagv0.4.0). - Binaries built by the workflow:
aarch64-apple-darwin(macOS),x86_64-unknown-linux-gnu.
Flow
1. Review what changed since the last release
git fetch --tags
last=$(git tag --sort=-v:refname | head -1)
echo "Last release: ${last:-<none>}"
git log --oneline ${last:+$last..}HEAD
Group commits into a short changelog (Features / Fixes / Other). Prefer the user's framing of "what shipped" over raw commit subjects. If nothing meaningful changed, say so and stop.
2. Pick the next version
Semver on root Cargo.toml → [workspace.package] version. Pre-1.0 (0.y.z), so y acts like "major" and z like "patch". Decide by scanning the conventional-commit types in git log <last-tag>..HEAD:
| Commits since last release | Bump | Example |
|---|---|---|
Any feat, or any breaking change (! / BREAKING CHANGE) |
minor | 0.4.0 → 0.5.0 |
Only fix / perf / refactor / chore / docs / test / build / ci (nothing users can newly invoke, nothing breaking) |
patch | 0.4.0 → 0.4.1 |
Rule of thumb: one feat or ! anywhere in the range forces a minor; an all-fixes/chores/docs range is a patch. Pre-1.0 keeps breaking changes in the minor slot (no major bump until 1.0). Confirm the version with the user if unsure.
This type-based decision assumes every commit follows Conventional Commits (
type(scope): summary), which thegit-workflowskill already enforces. If the range has non-conventional subjects you can't classify, fall back to judging by actual user-visible behavior — any new user-invocable capability → minor; otherwise patch — and lean on the user's framing of "what shipped" from step 1.
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.
- 4d ago First seen · 100 lines · 63 tokens per session scan A b9bf3edec1e7
release is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,180 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…