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/zhpeng24/devkit/deployment-operationsnpx skills add zhpeng24/devkit --skill deployment-operationsgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00057 | $0.00964 |
| Opus 5 | $0.00028 | $0.00482 |
| Sonnet 5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
deployment-operations 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Operations
Operate from observed state and an explicit target contract. Prefer the smallest reversible change that restores or advances the requested outcome.
Resolve the operating contract
- Read repository instructions, deployment docs, manifests, environment
examples, and the optional
.devkit/project.json. - Resolve the target environment, host or cluster, working directory, branch or artifact, runtime manager, health probes, and rollback unit.
- Treat project-profile values as defaults, not authorization. Never infer permission for production mutation, data deletion, secret rotation, volume removal, migration rollback, or another irreversible action.
- If target identity is still ambiguous and the next command can affect live traffic or data, stop and ask for that target. Read-only discovery can proceed.
Use references/deployment-playbook.md for runtime-specific commands and project
profile mappings. Use references/incident-response.md for outages and degraded
service.
Route the request
| Mode | Required outcome |
|---|---|
| Plan | Produce a target-specific sequence, evidence gates, rollback point, and stop conditions. |
| Development runtime | Start or reconcile the project-approved local processes and dependencies. |
| Deploy | Deliver a known commit, image, or package and verify user-visible readiness. |
| Diagnose | Locate the failing layer from read-only evidence before changing state. |
| Rollback | Restore a known-good artifact or configuration and repeat the same probes. |
| Harden | Improve secrets, permissions, resource limits, observability, or runbooks without inventing live state. |
Operate
- Preflight. Inspect worktree state, artifact identity, target reachability, runtime configuration, dependencies, capacity, and current health. Validate Compose, systemd, or Kubernetes configuration before applying it.
- Declare evidence. Name the exact success probes and the rollback boundary. A process being alive is not readiness; include dependency and user-path probes when the goal depends on them.
- Change one coherent unit. Update only the requested services or resources. Prefer rolling/recreate operations over teardown. Do not use volume deletion, force pushes, hard resets, or unreviewed migration reversal as shortcuts.
- Verify. Re-run the failed or target probe, then one upstream and one downstream check when applicable. Confirm the deployed commit, image digest, package version, or configuration revision.
- Record. Report target, artifact, commands, concise results, data or secrets touched, rollback status, and remaining risk. Update the project runbook when ports, environment variables, runtime contracts, or operator actions changed.
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.
- yesterday First seen · 89 lines · 57 tokens per session scan A be59c9313a4f
deployment-operations is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 964 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 2026-08-31.
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…