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/kodingdev/meridian/commitnpx skills add KodingDev/meridian --skill commitgit clone --depth 1 https://github.com/KodingDev/meridianWhat 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 | $0.00036 | $0.00978 |
| Opus 5 | $0.00018 | $0.00489 |
| Sonnet 5 | $0.00007 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Invariants
- Never commit secrets, environment files, local Meridian artifacts, or unintended generated/binary files.
- Never force-push or rewrite shared history without explicit authorization.
Commit flow
- Inspect
git status, staged and unstaged diffs, and recent commit style. - Identify the files belonging to the requested change. Ask only when staged scope is materially ambiguous; otherwise stage the intended files narrowly.
- Exclude local-only or unrelated files without reverting their contents.
- Draft the message per the conventions below.
- Commit without a redundant approval prompt.
- If push was explicitly requested, push to the current tracking branch. Ask before choosing a remote or branch that cannot be inferred, and before any destructive recovery from rejection.
- Move the
Statusline of any spec or sketch this work delivers toSHIPPED <sha>.
Both artifacts
They are read by an engineer who was not there: months later, holding the diff, with no memory of the work.
Every sentence stands alone. Describe what the code does and why it does it, in terms a reader holding only the diff can follow. "As discussed", "after the rebase", "addressed the review comment", "still failing from before" all fail that test: they point at a session the reader never saw. Circumstantial detail belongs in conversation instead.
Repository convention outranks this skill. Read recent merged commits and pull requests, and use the pull request template when one exists: its subject grammar, its sectioning, its label and issue-linking practice. Introduce no section the repository does not already use.
Commit messages
- Subject in the repository's convention, imperative mood, one line, no trailing period.
- A body when the change needs a reason: why it exists, what behavior changed. Self-evident changes take no body.
- One commit is one coherent change.
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 · 65 lines · 36 tokens per session scan A 471f1863e3d0
commit is a skill published in the GitHub repository KodingDev/meridian (5 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 978 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…