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/executenpx skills add KodingDev/meridian --skill executegit 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 | $0.00013 | $0.00699 |
| Opus 5 | $0.00006 | $0.00349 |
| Sonnet 5 | $0.00003 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
execute 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.
Execute
Implement the scope the user explicitly authorized. Invocation is approval to begin ordinary in-scope implementation; do not ask the user to approve entering the workflow again.
Invariants
- Do not claim completion without observing risk-appropriate verification.
- Do not trust delegated completion reports without inspecting the diff and evidence yourself.
- Preserve unrelated user changes and keep the diff inside the approved scope.
- Do not delete a migration source until every caller uses and verifies the replacement. If full cutover is not achievable, leave the legacy path intact and report the partial state.
- Do not push, deploy, delete data, force-push, or perform another unrequested external or irreversible action.
Process
1. Ground the work
Read the approved spec or supplied requirements, project instructions, relevant code, and current worktree state. Resolve ordinary reversible implementation details yourself. Ask only when a missing decision would materially change architecture, scope, risk, or an irreversible action.
2. Plan proportionately
Break multi-part work into dependency-ordered tasks. Keep a small change inline. Use meridian:delegate only for genuinely independent or context-heavy work where isolation materially improves execution; agent count is not evidence of diligence.
3. Implement and verify
For each task:
- Search for existing interfaces, utilities, tests, and conventions before adding competing logic.
- Implement the smallest durable change that satisfies the requirement.
- Exercise the highest practical real seam: focused tests, typecheck, build, CLI, service, or browser behavior as appropriate.
- If behavior fails unexpectedly, use
meridian:debugrather than stacking speculative patches. - Check the diff against scope and the spec's User Constraints.
- If a spec exists, append a concise Progress Log entry containing the task outcome, verification, deviations, and open concerns that a future agent could not recover from the diff.
What ships with it
2 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 · 65 lines · 13 tokens per session scan A 2c4e7492ed35
execute is a skill published in the GitHub repository KodingDev/meridian (5 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 699 once invoked, about $0.0001 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…