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/drn/dots/deploy-validatenpx skills add drn/dots --skill deploy-validategit clone --depth 1 https://github.com/drn/dotsWhat 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 | $0.00073 | $0.01384 |
| Opus 5 | $0.00036 | $0.00692 |
| Sonnet 5 | $0.00015 | $0.00277 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
deploy-validate 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 2d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-Deploy Health Validation
Validate that a deploy that has just landed is healthy: confirm it actually shipped what was intended, then check CI, rollout, error tracking, and monitoring — correlating every finding's timing against the deploy's start so pre-existing issues are not mistaken for regressions.
Run this after the user confirms the deploy has finished (this skill does not poll or wait for a deploy in progress).
Arguments
$ARGUMENTS- Optional: the deployed branch/tag/ref, and/or a deploy start timestamp. If omitted, detect the deployed ref the same waydeploy-auditwould and derive the start time from the deploy pipeline itself in Step 2.
Context
- Remote: !
git remote get-url origin 2>/dev/null | head -1 - Default branch: !
git branch -r 2>/dev/null | grep -oE 'origin/(main|master)' | head -1 - Current HEAD: !
git rev-parse --short HEAD 2>/dev/null | head -1 - Latest tag: !
git describe --tags --abbrev=0 2>/dev/null | head -1
Instructions
Work through the following steps in order — the timestamp correlation in Step 4 is what makes this validation trustworthy rather than a generic health-check dashboard.
Step 1: Confirm the deploy landed
Determine the deployed ref (from $ARGUMENTS or by asking, mirroring
deploy-audit's ref detection). Refs are treated as untrusted input for
shell purposes: if a ref contains characters outside [A-Za-z0-9._/-], do
not interpolate it directly into a shell command — quote it and confirm with
the user first.
Fetch it and confirm it now points at the commit/tag that was intended to ship — e.g. the deployed branch's SHA matches the base branch's SHA at the time of the deploy, or a release tag was created at the expected commit.
If the deployed ref does not match what was expected, stop and report this first — nothing downstream matters if the wrong thing shipped.
Step 2: Find the deploy pipeline and its start time
Use ToolSearch to find whatever CI/deploy tooling is available in this project (search terms like "circleci", "github actions", "pipeline", "deploy"). Find the pipeline/workflow run that performed this deploy and record:
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.
- 2d ago First seen · 152 lines · 73 tokens per session scan A 9af30601f6b5
deploy-validate is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 1,384 once invoked, about $0.0004 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…