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/jonathanung/strike/releasenpx skills add jonathanung/strike --skill releasegit clone --depth 1 https://github.com/jonathanung/strikeWhat 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 | $0.00045 | $0.00780 |
| Opus 5 | $0.00023 | $0.00390 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release (strike-cli)
Ship a version tag that triggers .github/workflows/release.yml (multi-arch archives + GitHub Release).
Preconditions
gh auth statusok; push rights to the repo that owns tags.- Working tree clean on an up-to-date
main(or explicit commit SHA to tag). - User confirmed version number (e.g.
v0.1.0) and that this is intentional.
Stop-and-ask if main CI is red, an open release-block issue exists, or the tag already exists.
Preflight
git fetch origin main --tags
git checkout main
git merge --ff-only origin/main
git status -sb # must be clean, main == origin/main
gh run list --branch main --limit 3 # latest CI success preferred
git tag -l 'v*' | tail -5
git log "$(git describe --tags --abbrev=0)..HEAD" --oneline
Load test-and-validate tier B (or C if trust-boundary commits dominate since last tag). Prefer green CI on main over re-running the full suite locally when CI is already success on HEAD.
Optional: load smoke for a quick product check.
Changelog
Draft the version entry from git log PREV..HEAD before tagging. Follow the
standard in CHANGELOG.md and docs/contributing.md: rename [Unreleased] to
[vX.Y.Z] - YYYY-MM-DD, add a fresh [Unreleased], and update the comparison
links. Commit and push that entry to main; the release workflow fails if the
tag has no matching non-empty entry.
Include:
- User-facing changes grouped under the standard categories
- Breaking/default changes (keybinds, config) if any
- Upgrade note when relevant
Do not ship install-only boilerplate or copy implementation-only commit activity into the changelog.
Tag and push
VERSION=v0.x.y # user-confirmed
git tag -a "$VERSION" -m "strike $VERSION
<one-line summary>
"
git push origin "$VERSION"
Never force-push tags. Never tag a dirty tree or a commit not on origin/main unless the user explicitly requests a pre-release from a branch.
Watch workflow
gh run list --workflow=release.yml --limit 3
gh run watch <id> --exit-status
gh release view "$VERSION"
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 · 103 lines · 45 tokens per session scan A a569a6bf770d
release is a skill published in the GitHub repository jonathanung/strike (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 780 once invoked, about $0.0002 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…