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/hafeok/product-cli/releasenpx skills add Hafeok/product-cli --skill releasegit clone --depth 1 https://github.com/Hafeok/product-cliWhat 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 | $0.00083 | $0.02313 |
| Opus 5 | $0.00042 | $0.01156 |
| Sonnet 5 | $0.00017 | $0.00463 |
| Haiku 4.5 | $0.00008 | $0.00231 |
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 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release the Product CLI
The release pipeline (.github/workflows/release.yml, autogenerated by dist generate — don't hand-edit it) is driven by cargo-dist. It fires when a git
tag matching **[0-9]+.[0-9]+.[0-9]+* is pushed and builds the GitHub Release
artifacts from the tagged commit. This is a Cargo workspace, and cargo-dist
runs in lockstep mode: pushing vX.Y.Z releases every dist-able package in the
workspace at version X.Y.Z (it errors if a dist-able package's version doesn't
match the tag). The binary is product, in the product-cli package.
The version sources — keep them in lockstep at X.Y.Z
There is no root version — root Cargo.toml is [workspace]-only. The
version is spread across these files, and they must all agree:
| File | Field | Why |
|---|---|---|
product-core/Cargo.toml |
line 3 version |
published lib version |
product-mcp/Cargo.toml |
line 3 version |
published lib version |
product-cli/Cargo.toml |
line 3 version |
the dist-able binary package — cargo-dist matches the tag against this |
.product/config.toml |
line 2 version |
Product config (mirrors the release) |
product-cli/Cargo.toml |
lines 20–21 internal version on the product-core/product-mcp path deps |
lockstep target — see below |
product-mcp/Cargo.toml |
line 20 internal version on the product-core path dep |
lockstep target — see below |
xtask/Cargo.toml stays at 0.1.0 — it's an internal build-helper, not
dist-able, not released. Do not bump it.
The internal path-dep versions matter. Since v0.3.0, the intra-workspace
path deps carry an explicit version (e.g.
product-core = { path = "../product-core", version = "0.3.0" }). This is what
lets cargo deny check's wildcards = "deny" ban pass on the publishable
crates. If you bump the package versions but forget these, Product CI's
cargo-deny step goes red (and a real cargo publish would mismatch). They are
the easiest thing to miss — there's no test that pins them, only the CI gate.
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 · 194 lines · 83 tokens per session scan A 3f987ffd8047
release is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 2,313 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 2026-08-31.
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…