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/uxname/litestack/commitnpx skills add uxname/LiteStack --skill commitgit clone --depth 1 https://github.com/uxname/LiteStackWhat 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 | $0.00077 | $0.00965 |
| Opus 5 | $0.00039 | $0.00483 |
| Sonnet 5 | $0.00015 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
commit 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants to commit work done across LiteStack. Because backend/ and frontend/
are separate git repositories (submodules), a meta-level commit is a few ordered steps,
not one git commit. Get the order right or the meta-repo will point at commits that were
never pushed.
Step 0: Write the session retrospective (mandatory)
Before anything else, run the /retro skill to record what went badly this session into
docs/retro/. This is the project's mistake-memory that future agents read before touching
code (root AGENTS.md → START HERE). Skip the file write only if the session was
genuinely clean — but always run the skill so that judgement is made deliberately, not by
omission. The retro file is a meta-repo file; it gets staged and committed in Step 4–5 below.
Step 1: Detect the operating mode
Read root .agents/OPERATING-MODE.md. In short:
git config -f .gitmodules submodule.liteend-go.url
git config -f .gitmodules submodule.litefront.url
- URLs point at canonical
uxname/*→ TEMPLATE mode (push submodules to upstream). - URLs point at your own repos → DERIVED mode (push submodules to your repos).
If you are unsure which mode applies or whether you should push, ask the user in plain language before pushing.
Step 2: See what changed and where
git status # at meta root: shows which submodules are dirty + meta files
git submodule status
Step 3: Commit inside each changed submodule
For each submodule that has changes (backend and/or frontend):
cd <submodule>
# Run that project's own gate FIRST, from its AGENTS.md:
# backend → task check (and task test:cov before pushing)
# frontend → npm run check (verify:push runs on pre-push)
git add -A && git commit # conventional commits; the pre-commit hook re-runs the gate
git push # push to the submodule's remote (per the detected mode)
cd ..
Do not skip the submodule's pre-commit / pre-push hooks. Never use --no-verify —
there is no CI behind them.
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 · 104 lines · 77 tokens per session scan A bcfc62119c20
commit is a skill published in the GitHub repository uxname/LiteStack (2 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 965 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…